| 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. |
