Amazing Books
Temporary Blank

Monday, April 16, 2012

Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering






Nikola K. Kasabov
A Bradford Book
The MIT Press
Cambridge, Massachusetts
London, England

Contents
Foreword by Shun-ichi Amari xi
Preface xiii
1 The Faculty of Knowledge Engineering and Problem Solving 1
1.1 Introduction to AI paradigms 1
1.2 Heuristic problem solving; genetic algorithms 3
1.3 Why expert systems, fuzzy systems, neural networks, and hybrid systems
for knowledge engineering and problem solving?
14
1.4 Generic and specific AI problems: Pattern recognition and classification 19
1.5 Speech and language processing 28
1.6 Prediction 42
1.7 Planning, monitoring, diagnosis, and control 49
1.8 Optimization, decision making, and games playing 57
1.9 A general approach to knowledge engineering 65
1.10 Problems and exercises 68
1.11 Conclusion 72
1.12 Suggested reading 732 Knowledge Engineering and Symbolic Artificial Intelligence 75
2.1 Data, information, and knowledge: Major issues in knowledge engineering 75
2.2 Data analysis, data representation, and data transformation 80
2.3 Information structures and knowledge representation 89
2.4 Methods for symbol manipulation and inference: Inference as matching;
inference as a search
100
2.5 Propositional logic 110
2.6 Predicate logic: PROLOG 113
2.7 Production systems 118
2.8 Expert systems 128
2.9 Uncertainties in knowledge-based systems: Probabilistic methods 132
2.10 Nonprobabilistic methods for dealing with uncertainties 140
2.11 Machine-learning methods for knowledge engineering 146
2.12 Problems and exercises 155
2.13 Conclusion 164
2.14 Suggested reading 164
3 From Fuzzy Sets to Fuzzy Systems 167
3.1 Fuzzy sets and fuzzy operations 167
3.2 Fuzziness and probability;
conceptualizing in fuzzy terms; the
extension principle
175
3.3 Fuzzy relations and fuzzy
implications; fuzzy propositions and
fuzzy logic
184
3.4 Fuzzy rules, fuzzy inference
methods, fuzzification and
defuzzification
192
3.5 Fuzzy systems as universal
approximators; Interpolation of
fuzzy rules
205
3.6 Fuzzy information retrieval and
fuzzy databases
208
3.7 Fuzzy expert systems 215
3.8 Pattern recognition and
classification, fuzzy clustering,
image and speech processing
223
3.9 Fuzzy systems for prediction 229
3.10 Control, monitoring, diagnosis,
and planning
230
3.11 Optimization and decision
making
234
3.12 Problems and exercises 236
3.13 Conclusion 248
3.14 Suggested reading 249
4 Neural Networks: Theoretical and
Computational Models
251
4.1 Real and artificial neurons 251
4.2 Supervised learning in neural
networks: Perceptrons and
multilayer perceptrons
267
4.3 Radial basis functions, time-
delay neural networks, recurrent
networks
282
4.4 Neural network models for
unsupervised learning:
288 4.5 Kohonen self-organizing
topological maps
293
4.6 Neural networks as associative
memories
300
4.7 On the variety of neural network
models
307
4.8 Fuzzy neurons and fuzzy neural
networks
314
4.9 Hierarchical and modular
connectionist systems
320
4.10 Problems 323
4.11 Conclusion 3284.12 Suggested reading 329

Page ix
5 Neural Networks for Knowledge Engineering and Problem Solving 331
5.1 Neural networks as a problem-solving paradigm 331
5.2 Connectionist expert systems 340
5.3 Connectionist models for knowledge acquisition: One rule is worth a
thousand data examples
347
5.4 Symbolic rules insertion in neural networks: Connectionist production
systems
359
5.5 Connectionist systems for pattern recognition and classification; image
processing
365
5.6 Connectionist systems for speech processing 375
5.7 Connectionist systems for prediction 388
5.8 Connectionist systems for monitoring, control, diagnosis, and planning 398
5.9 Connectionist systems for optimization and decision making 402
5.10 Connectionist systems for modeling strategic games 405
5.11 Problems 409
5.12 Conclusions 418
5.13 Suggested reading 4186 Hybrid Symbolic, Fuzzy, and Connectionist Systems: Toward Comprehensive
Artificial Intelligence
421
6.1 The hybrid systems paradigm 421
6.2 Hybrid connectionist production systems 429
6.3 Hybrid connectionist logic programming systems 433
6.4 Hybrid fuzzy connectionist production systems 435
6.5 ("Pure") connectionist production systems: The NPS architecture
(optional)
442
6.6 Hybrid systems for speech and language processing 455
6.7 Hybrid systems for decision making 460
6.8 Problems 462
6.9 Conclusion 473
6.10 Suggested reading 473
7 Neural Networks, Fuzzy Systems and Nonlinear Dynamical Systems Chaos;
Toward New Connectionist and Fuzzy Logic Models
475
7.1 Chaos 475
7.2 Fuzzy systems and chaos: New developments in fuzzy systems 481
Page x
7.3 Neural networks and chaos: New developments in neural networks 486
7.4 Problems 497
7.5 Conclusion 502
7.6 Suggested reading 503
Appendixes 505
References 523
Glossary 539
Index 547


Neural network - Wikipedia, the free encyclopedia
Neural Networks
Fuzzy logic - Wikipedia, the free encyclopedia
Fuzzy Logic Tutorial - An Introduction

Neural Networks Theory
Introduction to Fuzzy Sets, Fuzzy Logic, and Fuzzy Control Systems
Other Neural Network Books
Other Fuzzy Logic Books
Download

No comments:

Post a Comment

Related Posts with Thumbnails
There was an error in this gadget

Put Your Ads Here!
There was an error in this gadget