## Expert Systems and Probabilistic Network ModelsArtificial intelligence and expert systems have seen a great deal of research in recent years, much of which has been devoted to methods for incorporating uncertainty into models. This book is devoted to providing a thorough and up-to-date survey of this field for researchers and students. |

### What people are saying - Write a review

User Review - Flag as inappropriate

expert book

### Contents

Introduction | 1 |

12 What Is an Expert System? | 2 |

13 Motivating Examples | 3 |

14 Why Expert Systems? | 7 |

15 Types of Expert System | 8 |

16 Components of an Expert System | 10 |

17 Developing an Expert System | 14 |

18 Other Areas of AI | 16 |

77 Conditionally Specified Probabilistic Models | 298 |

Exercises | 311 |

Exact Propagation in Probabilistic Network Models | 317 |

82 Propagation of Evidence | 318 |

83 Propagation in Polytrees | 321 |

84 Propagation in MultiplyConnected Networks | 342 |

86 Clustering Methods | 351 |

87 Propagation Using Join Trees | 366 |

19 Concluding Remarks | 20 |

RuleBased Expert Systems | 21 |

22 The Knowledge Base | 22 |

23 The Inference Engine | 28 |

24 Coherence Control | 48 |

25 Explaining Conclusions | 52 |

26 Some Applications | 53 |

27 Introducing Uncertainty | 65 |

Probabilistic Expert Systems | 69 |

32 Some Concepts in Probability Theory | 71 |

33 Generalized Rules | 85 |

34 Introducing Probabilistic Expert Systems | 86 |

35 The Knowledge Base | 91 |

36 The Inference Engine | 102 |

37 Coherence Control | 104 |

38 Comparing RuleBased and Probabilistic Expert Systems | 106 |

Exercises | 108 |

Some Concepts of Graphs | 113 |

42 Basic Concepts and Definitions | 114 |

43 Characteristics of Undirected Graphs | 118 |

44 Characteristics of Directed Graphs | 122 |

45 Triangulated Graphs | 129 |

46 Cluster Graphs | 139 |

47 Representation of Graphs | 144 |

48 Some Useful Graph Algorithms | 158 |

Exercises | 172 |

Building Probabilistic Models | 175 |

52 Graph Separation | 177 |

53 Some Properties of Conditional Independence | 184 |

54 Special Types of Input Lists | 192 |

55 Factorizations of the JPD | 195 |

56 Constructing the JPD | 200 |

Appendix to Chapter 5 | 204 |

Exercises | 206 |

Graphically Specified Models | 211 |

62 Some Definitions and Questions | 213 |

63 Undirected Graph Dependency Models | 218 |

64 Directed Graph Dependency Models | 237 |

65 Independence Equivalent Graphical Models | 252 |

66 Expressiveness of Graphical Models | 259 |

Exercises | 262 |

Extending Graphically Specified Models | 267 |

72 Models Specified by Multiple Graphs | 269 |

73 Models Specified by Input Lists | 275 |

74 Multifactorized Probabilistic Models | 279 |

76 Multifactorized Normal Models | 292 |

88 GoalOriented Propagation | 377 |

89 Exact Propagation in Gaussian Networks | 382 |

Exercises | 387 |

Approximate Propagation Methods | 393 |

92 Intuitive Basis of Simulation Methods | 394 |

93 General Frame for Simulation Methods | 400 |

94 AcceptanceRejection Sampling Method | 406 |

95 Uniform Sampling Method | 409 |

96 The Likelihood Weighing Sampling Method | 411 |

97 BackwardForward Sampling Method | 413 |

98 Markov Sampling Method | 415 |

99 Systematic Sampling Method | 419 |

910 Maximum Probability Search Method | 429 |

911 Complexity Analysis | 439 |

Exercises | 440 |

Symbolic Propagation of Evidence | 443 |

102 Notation and Basic Framework | 445 |

103 Automatic Generation of Symbolic Code | 447 |

104 Algebraic Structure of Probabilities | 454 |

105 Symbolic Propagation Through Numeric Computations | 455 |

106 GoalOriented Symbolic Propagation | 464 |

107 Symbolic Treatment of Random Evidence | 470 |

108 Sensitivity Analysis | 472 |

109 Symbolic Propagation in Gaussian Bayesian Networks | 474 |

Exercises | 478 |

Learning Bayesian Networks | 481 |

112 Measuring the Quality of a Bayesian Network Model | 484 |

113 Bayesian Quality Measures | 486 |

114 Bayesian Measures for Multinomial Networks | 490 |

115 Bayesian Measures for Multinomial Networks | 499 |

116 Minimum Description Length Measures | 506 |

117 Information Measures | 509 |

119 Bayesian Network Search Algorithms | 511 |

1110 The Case of Incomplete Data | 513 |

Bayesian Statistics | 515 |

Exercises | 525 |

Case Studies | 529 |

122 Pressure Tank System | 530 |

123 Power Distribution System | 542 |

124 Damage of Concrete Structures | 550 |

The Gaussian Model | 562 |

Exercises | 567 |

List of Notation | 573 |

581 | |

597 | |

### Other editions - View all

Expert Systems and Probabilistic Network Models Enrique Castillo,Jose M. Gutierrez,Ali S. Hadi Limited preview - 2012 |

Expert Systems and Probabilistic Network Models Enrique Castillo,Jose M. Gutierrez,Ali S. Hadi No preview available - 2011 |

Expert Systems and Probabilistic Network Models Enrique Castillo,Jose M Gutierrez,Ali S Hadi No preview available - 1996 |

### Common terms and phrases

associated Bayesian network models calculate chain of cliques chain rule Chapter CISs clustering algorithm compute conditional independence conditionally independent Consider contains corresponding covariance matrix current goal object D-separation defined Definition dependency model disease evidential nodes example factorization given in Figure given in Table go to Step graph in Figure graphical human experts illustrated implies inference engine initial input list instantiations iteration step join tree knowledge base marginal probabilities Markov network messages Modus Ponens Modus Tollens moral graph neighbors node Xi normal Note numerical values obtain p(xi parents path perfect numbering polynomial polytree possible values posterior probability potential functions potential representation prior probability distribution probabilistic expert systems probabilistic model problem quality measure random variables sampling method satisfy Section set of CPDs set of nodes set of variables shown in Figure simulation subset Suppose symbolic parameters symbolic propagation symptoms Theorem triangulated graph undirected graph