Computational Intelligence

by Rutkowski, Leszek

• ISBN13: 9783540762874
• ISBN10: 3540762876
• Edition: 1st
• Format: Hardcover
• Copyright: 2008-07-04
• Publisher: Springer Verlag

Summary

"This book focuses on various techniques of computational intelligence, both single ones and those which form hybrid methods. Those techniques are today commonly applied issues of artificial intelligence, e.g. to process speech and natural language, build expert systems and robots."--BOOK JACKET.

Table of Contents

Foreword	p. v
Introduction	p. 1
Selected issues of artificial intelligence	p. 7
Introduction	p. 7
An outline of artificial intelligence history	p. 8
Expert systems	p. 10
Robotics	p. 11
Processing of speech and natural language	p. 13
Heuristics and research strategies	p. 15
Cognitivistics	p. 16
Intelligence of ants	p. 17
Artificial life	p. 19
Bots	p. 20
Perspectives of artificial intelligence development	p. 22
Notes	p. 23
Methods of knowledge representation using rough sets	p. 25
Introduction	p. 25
Basic terms	p. 27
Set approximation	p. 34
Approximation of family of sets	p. 44
Analysis of decision tables	p. 46
Application of LERS software	p. 54
Notes	p. 61
Methods of knowledge representation using type-1 fuzzy sets	p. 63
Introduction	p. 63
Basic terms and definitions of fuzzy sets theory	p. 63
Operations on fuzzy sets	p. 76
The extension principle	p. 83
Fuzzy numbers	p. 87
Triangular norms and negations	p. 96
Fuzzy relations and their properties	p. 108
Approximate reasoning	p. 112
Basic rules of inference in binary logic	p. 112
Basic rules of inference in fuzzy logic	p. 114
Inference rules for the Mamdani model	p. 118
Inference rules for the logical model	p. 119
Fuzzy inference systems	p. 122
Rules base	p. 123
Fuzzification block	p. 124
Inference block	p. 125
Defuzzification block	p. 131
Application of fuzzy sets	p. 134
Fuzzy Delphi method	p. 134
Weighted fuzzy Delphi method	p. 138
Fuzzy PERT method	p. 139
Decision making in a fuzzy environment	p. 142
Notes	p. 153
Methods of knowledge representation using type-2 fuzzy sets	p. 155
Introduction	p. 155
Basic definitions	p. 156
Footprint of uncertainty	p. 160
Embedded fuzzy sets	p. 162
Basic operations on type-2 fuzzy sets	p. 164
Type-2 fuzzy relations	p. 169
Type reduction	p. 172
Type-2 fuzzy inference systems	p. 178
Fuzzification block	p. 178
Rules base	p. 180
Inference block	p. 180
Notes	p. 186
Neural networks and their learning algorithms	p. 187
Introduction	p. 187
Neuron and its models	p. 188
Structure and functioning of a single neuron	p. 188
Perceptron	p. 190
Adaline model	p. 196
Sigmoidal neuron model	p. 202
Hebb neuron model	p. 206
Multilayer feed-forward networks	p. 208
Structure and functioning of the network	p. 208
Backpropagation algorithm	p. 210
Backpropagation algorithm with momentum term	p. 218
Variable-metric algorithm	p. 220
Levenberg-Marquardt algorithm	p. 221
Recursive least squares method	p. 222
Selection of network architecture	p. 225
Recurrent neural networks	p. 232
Hopfield neural network	p. 232
Hamming neural network	p. 236
Multilayer neural networks with feedback	p. 238
BAM network	p. 238
Self-organizing neural networks with competitive learning	p. 240
WTA neural networks	p. 240
WTM neural networks	p. 246
ART neural networks	p. 250
Radial-basis function networks	p. 254
Probabilistic neural networks	p. 261
Notes	p. 263
Evolutionary algorithms	p. 265
Introduction	p. 265
Optimization problems and evolutionary algorithms	p. 266
Type of algorithms classified as evolutionary algorithms	p. 267
Classical genetic algorithm	p. 268
Evolution strategies	p. 289
Evolutionary programming	p. 307
Genetic programming	p. 309
Advanced techniques in evolutionary algorithms	p. 310
Exploration and exploitation	p. 310
Selection methods	p. 311
Scaling the fitness function	p. 314
Specific reproduction procedures	p. 315
Coding methods	p. 317
Types of crossover	p. 320
Types of mutation	p. 322
Inversion	p. 323
Evolutionary algorithms in the designing of neural networks	p. 323
Evolutionary algorithms applied to the learning of weights of neural networks	p. 324
Evolutionary algorithms for determining the topology of the neural network	p. 327
Evolutionary algorithms for learning weights and determining the topology of the neural network	p. 330
Evolutionary algorithms vs fuzzy systems	p. 332
Fuzzy systems for evolution control	p. 333
Evolution of fuzzy systems	p. 335
Notes	p. 344
Data clustering methods	p. 349
Introduction	p. 349
Hard and fuzzy partitions	p. 350
Distance measures	p. 354
HCM algorithm	p. 357
FCM algorithm	p. 359
PCM algorithm	p. 360
Gustafson-Kessel algorithm	p. 361
FMLE algorithm	p. 363
Clustering validity measures	p. 364
Illustration of operation of data clustering algorithms	p. 367
Notes	p. 369
Neuro-fuzzy systems of Mamdani, logical and Takagi-Sugeno type	p. 371
Introduction	p. 371
Description of simulation problems used	p. 372
Polymerization	p. 372
Modeling a static non-linear function	p. 373
Modeling a non-linear dynamic object (Nonlinear Dynamic Problem - NDP)	p. 373
Modeling the taste of rice	p. 374
Distinguishing of the brand of wine	p. 374
Classification of iris flower	p. 374
Neuro-fuzzy systems of Mamdani type	p. 375
A-type systems	p. 375
B-type systems	p. 377
Mamdani type systems in modeling problems	p. 378
Neuro-fuzzy systems of logical type	p. 390
M1-type systems	p. 392
M2-type systems	p. 399
M3-type systems	p. 405
Neuro-fuzzy systems of Takagi-Sugeno type	p. 410
M1-type systems	p. 413
M2-type systems	p. 414
M3-type systems	p. 416
Learning algorithms of neuro-fuzzy systems	p. 418
Comparison of neuro-fuzzy systems	p. 435
Models evaluation criteria taking into account their complexity	p. 437
Criteria isolines method	p. 439
Notes	p. 448
Flexible neuro-fuzzy systems	p. 449
Introduction	p. 449
Soft triangular norms	p. 449
Parameterized triangular norms	p. 452
Adjustable triangular norms	p. 456
Flexible systems	p. 461
Learning algorithms	p. 463
Basic operators	p. 470
Membership functions	p. 471
Constraints	p. 473
H-functions	p. 473
Simulation examples	p. 479
Polymerization	p. 480
Modeling the taste of rice	p. 480
Classification of iris flower	p. 482
Classification of wine	p. 484
Notes	p. 492
References	p. 495
Table of Contents provided by Ingram. All Rights Reserved.