Preface
Acknowledgments
1 Evolutionary Systems
1.1 Pillars of Evolutionary Theory 2
1.2 The Genotype 5
1.3 Artificial Evolution 13
1.4 Genetic Representations 16
1.5 Initial Population 21
1.6 Fitness Functions 22
1.7 Selection and Reproduction 23
1.8 Genetic Operators 26
1.9 Evolutionary Measures 29
1.10 Types of Evolutionary Algorithms 33
1.11 Schema Theory 37
1.12 Human-Competitive Evolution 39
1.13 Evolutionary Electronics 42
1.14 Lessons from Evolutionary Electronics 43
1.15 The Role of Abstraction 45
1.16 Analog and Digital Circuits 49
1.17 Extrinsic and Intrinsic Evolution 53
1.18 Digital Design 58
1.19 Evolutionary Digital Design 62
1.20 Analog Design 77
1.21 Evolutionary Analog Design 79
1.22 Multiple Objectives and Constraints 85
1.23 Design Verification 90
1.24 Closing Remarks 92
1.25 Suggested Readings 97
2 Cellular Systems
2.1 The Basic Ingredients 101
2.2 Cellular Automata 107
2.3 Modeling with Cellular Systems 110
2.4 Some Classic Cellular Automata 118
2.5 Other Cellular Systems 124
2.6 Computation 134
2.7 Artificial Life 138
2.8 Complex Systems 145
2.9 Analysis and Synthesis of Cellular Systems 153
2.10 Closing Remarks 159
2.11 Suggested Readings 160
3 Neural Systems
3.1 Biological Nervous Systems 167
3.2 Artificial Neural Networks 175
3.3 Neuron Models 177
3.4 Architecture 189
3.5 Signal Encoding 191
3.6 Synaptic Plasticity 196
3.7 Unsupervised Learning 198
3.8 Supervised Learning 219
3.9 Reinforcement Learning 235
3.10 Evolution of Neural Networks 238
3.11 Neural Hardware 250
3.12 Hybrid Neural Systems 256
3.13 Closing Remarks 261
3.14 Suggested Readings 265
4 Developmental Systems
4.1 Potential Advantages of a Developmental Representation 270
4.2 Rewriting Systems 272
4.3 Synthesis of Developmental Systems 296
4.4 Evolution and Development 298
4.5 Defining Artificial Evolutionary Developmental Systems 299
4.6 Evolutionary Rewriting Systems 301
4.7 Evolutionary Developmental Programs 310
4.8 Evolutionary Developmental Processes 315
4.9 Closing Remarks 332
4.10 Suggested Readings 334
5 Immune Systems
5.1 How Biological Immune Systems Work 337
5.2 The Constituents of Biological Immune Systems 353
5.3 Lessons for Artificial Immune Systems 366
5.4 Algorithms and Applications 373
5.5 Shape Space 375
5.6 Negative Selection Algorithm 384
5.7 Clonal Selection Algorithm 388
5.8 Examples 390
5.9 Closing Remarks 395
5.10 Suggested Readings 396
6 Behavioral Systems
6.1 Behavior in Cognitive Science 400
6.2 Behavior in Artificial Intelligence 403
6.3 Behavior-Based Robotics 407
6.4 Biological Inspiration for Robots 419
6.5 Robots as Biological Models 437
6.6 Robot Learning 449
6.7 Evolution of Behavioral Systems 460
6.8 Evolution and Learning in Behavioral Systems 482
6.9 Evolution and Neural Development in Behavioral Systems 494
6.10 Coevolution of Body and Control 499
6.11 Toward Self-Reproduction 504
6.12 Simulation and Reality 507
6.13 Closing Remarks 511
6.14 Suggested Readings 513
7 Collective Systems
7.1 Biological Self-Organization 516
7.2 Particle Swarm Optimization 524
7.3 Ant Colony Optimization 527
7.4 Swarm Robotics 531
7.5 Coevolutionary Dynamics: Biological Models 547
7.6 Artificial Evolution of Competing Systems 554
7.7 Artificial Evolution of Cooperation 572
7.8 Closing Remarks 581
7.9 Suggested Readings 583
Conclusion
References
Index |
