Artificial Intelligence, 3rd edition
A Guide to Intelligent Systems
By Michael Negnevitsky
September 2011
Pearson Education
Distrubuted by Trans-Atlantic Publications Inc.
ISBN: 9781408225745
479 pages, Illustrated
$99.50 Paper Original
Negnevitsky shows students how to build intelligent systems drawing on techniques from knowledge-based systems, neural networks, fuzzy systems, evolutionary computation and now also intelligent agents. The principles behind these techniques are explained without resorting to complex mathematics, showing how the various techniques are implemented, when they are useful and when they are not. No particular programming language is assumed and the book does not tie itself to any of the software tools available. However, available tools and their uses are described, and program examples are given in Java.
The lack of assumed prior knowledge makes this book ideal for any introductory courses in artificial intelligence or intelligent systems design, while the contemporary coverage means more advanced students will benefit by discovering the latest state-of-the-art techniques, particularly in intelligent agents and knowledge discovery.
Contents
Preface xii
New to this edition xiii
Overview of the book xiv
Acknowledgements xvii
1 Introduction to knowledge-based intelligent systems 1
1.1 Intelligent machines, or what machines can do 1
1.2 The history of artificial intelligence, or from the ‘Dark Ages’
to knowledge-based systems 4
1.3 Summary 17
Questions for review 21
References 22
2 Rule-based expert systems 25
2.1 Introduction, or what is knowledge? 25
2.2 Rules as a knowledge representation technique 26
2.3 The main players in the expert system development team 28
2.4 Structure of a rule-based expert system 30
2.5 Fundamental characteristics of an expert system 33
2.6 Forward chaining and backward chaining inference
techniques 35
2.7 MEDIA ADVISOR: a demonstration rule-based expert system 41
2.8 Conflict resolution 47
2.9 Advantages and disadvantages of rule-based expert systems 50
2.10 Summary 51
Questions for review 53
References 54
3 Uncertainty management in rule-based expert systems 55
3.1 Introduction, or what is uncertainty? 55
3.2 Basic probability theory 57
3.3 Bayesian reasoning 61
3.4 FORECAST: Bayesian accumulation of evidence 65
3.5 Bias of the Bayesian method 72
3.6 Certainty factors theory and evidential reasoning 74
3.7 FORECAST: an application of certainty factors 80
3.8 Comparison of Bayesian reasoning and certainty factors 82
3.9 Summary 83
Questions for review 85
References 85
4 Fuzzy expert systems 87
4.1 Introduction, or what is fuzzy thinking? 87
4.2 Fuzzy sets 89
4.3 Linguistic variables and hedges 94
4.4 Operations of fuzzy sets 97
4.5 Fuzzy rules 103
4.6 Fuzzy inference 106
4.7 Building a fuzzy expert system 114
4.8 Summary 125
Questions for review 126
References 127
Bibliography 127
5 Frame-based expert systems 131
5.1 Introduction, or what is a frame? 131
5.2 Frames as a knowledge representation technique 133
5.3 Inference in frame-based experts 138
5.4 Methods and demons 142
5.5 Interaction of frames and rules 146
5.6 Buy Smart: a frame-based expert system 149
5.7 Summary 161
Questions for review 163
References 163
Bibliography 164
6 Artificial neural networks 165
6.1 Introduction, or how the brain works 165
6.2 The neuron as a simple computing element 168
6.3 The perceptron 170
6.4 Multilayer neural networks 175
6.5 Accelerated learning in multilayer neural networks 185
6.6 The Hopfield network 188
6.7 Bidirectional associative memories 196
6.8 Self-organising neural networks 200
6.9 Summary 212
Questions for review 215
References 216
7 Evolutionary computation 219
7.1 Introduction, or can evolution be intelligent? 219
7.2 Simulation of natural evolution 219
7.3 Genetic algorithms 222
7.4 Why genetic algorithms work 232
7.5 Case study: maintenance scheduling with genetic
algorithms 235
7.6 Evolutionary strategies 242
7.7 Genetic programming 245
7.8 Summary 254
Questions for review 255
References 256
Bibliography 257
8 Hybrid intelligent systems 259
8.1 Introduction, or how to combine German mechanics
with Italian love 259
8.2 Neural expert systems 261
8.3 Neuro-fuzzy systems 268
8.4 ANFIS: Adaptive Neuro-Fuzy Inference System 277
8.5 Evolutionary neural networks 285
8.6 Fuzzy evolutionary systems 290
8.7 Summary 296
Questions for review 297
References 298
9 Knowledge engineering 301
9.1 Introduction, or what is knowledge engineering? 301
9.2 Will an expert system work for my problem? 308
9.3 Will a fuzzy expert system work for my problem? 317
9.4 Will a neural network work for my problem? 323
9.5 Will genetic algorithms work for my problem?
9.6 Will a hybrid intelligent system work for my problem?
9.7 Summary
Questions for review
References
10 Data mining and knowledge discovery
10.1 Introduction, or what is data mining?
10.2 Statistical methods and data visualisation
10.3 Principal components analysis
10.4 Relational databases and database queries
10.5 The data warehouse and multidimensional data analysis
10.6 Decision trees
10.7 Association rules and market basket analysis
10.8 Summary
Questions for review
References
Glossary
Appendix
Index
Return to main page of Trans-Atlantic Publications