Table of contents for Bio-inspired artificial intelligence : theories, methods, and technologies / Dario Floreano and Claudio Mattiussi.

Bibliographic record and links to related information available from the Library of Congress catalog.

Note: Contents data are machine generated based on pre-publication provided by the publisher. Contents may have variations from the printed book or be incomplete or contain other coding.


Counter
Contents
Preface 1
Acknowledgments 4
1 Evolutionary Systems 9
1.1 Pillars of Evolutionary Theory 11
1.2 The Genotype 16
1.3 Artificial Evolution 30
1.4 Genetic Representations 33
1.5 Initial Population 42
1.6 Fitness Functions 44
1.7 Selection and Reproduction 46
1.8 Genetic Operators 50
1.9 Evolutionary Measures 56
ii Contents
1.10 Types of Evolutionary Algorithms 61
1.11 Schema Theory 66
1.12 Human-Competitive Evolution 70
1.13 Evolutionary Electronics 76
1.14 Lessons from evolutionary electronics 78
1.15 The role of abstraction 81
1.16 Analog and Digital circuits 87
1.17 Extrinsic and intrinsic evolution 93
1.18 Digital design 100
1.19 Evolutionary digital design 105
1.20 Analog design 128
1.21 Evolutionary analog design 132
1.22 Multiple objectives and constraints 140
1.23 Design verification 147
1.24 Closing remarks 151
1.25 Suggested readings 159
2 Cellular Systems 165
2.1 The basic ingredients 166
2.2 Cellular Automata 174
2.3 Modeling with cellular systems 179
2.4 Some classical CA 190
Contents iii
2.5 Other cellular systems 198
2.6 Computation 212
2.7 Artificial life 219
2.8 Complex systems 230
2.9 Analysis and synthesis of cellular systems 241
2.10 Closing remarks 250
2.11 Suggested readings 251
3 Neural Systems 255
3.1 Biological Nervous Systems 260
3.2 Artificial Neural Networks 273
3.3 Neuron models 277
3.4 Architecture 294
3.5 Signal Encoding 297
3.6 Synaptic Plasticity 304
3.7 Unsupervised Learning 308
3.8 Supervised Learning 340
3.9 Reinforcement Learning 364
3.10 Evolution of Neural Networks 368
3.11 Neural Hardware 388
3.12 Hybrid Neural Systems 399
3.13 Closing remarks 405
iv Contents
3.14 Suggested readings 412
4 Developmental Systems 417
4.1 Potential advantages of a developmental representation 418
4.2 Rewriting systems 422
4.3 Synthesis of developmental systems 458
4.4 Evolution and development 461
4.5 Defining artificial evolutionary developmental systems 464
4.6 Evolutionary rewriting systems 467
4.7 Evolutionary developmental programs 481
4.8 Evolutionary developmental processes 487
4.9 Closing remarks 511
5 Immune Systems 517
5.1 How biological immune systems work 521
5.2 The constituents of biological immune systems 545
5.3 Lessons for artificial immune systems 566
5.4 Algorithms and applications 576
5.5 Shape space 580
5.6 Negative selection algorithm 594
5.7 Clonal selection algorithm 599
5.8 Examples 602
Contents v
5.9 Closing remarks 611
5.10 Suggested readings 613
6 Behavioral Systems 615
6.1 Behavior in Cognitive Science 616
6.2 Behavior in Artificial Intelligence 623
6.3 Behavior-Based Robotics 629
6.4 Biological Inspiration for Robots 646
6.5 Robots as Biological Models 674
6.6 Robot Learning 694
6.7 Evolution of Behavioral Systems 713
6.8 Evolution and Learning in Behavioral Systems 745
6.9 Evolution and Neural Development in Behavioral Systems 764
6.10 Co-evolution of Body and Control 772
6.11 Towards Self-Reproduction 780
6.12 Simulation and Reality 784
6.13 Closing remarks 791
6.14 Suggested Readings 794
7 Collective Systems 797
7.1 Biological Self-Organization 799
7.2 Particle Swarm Optimization 811
vi Contents
7.3 Ant Colony Optimization 817
7.4 Swarm Robotics 823
7.5 Co-evolutionary Dynamics: Biological models 848
7.6 Artificial Evolution of Competing Systems 859
7.7 Artificial Evolution of Cooperation 886
7.8 Closing Remarks 901
7.9 Suggested Readings 905
Conclusion 907
Bibliography 913
Index 1020

Library of Congress Subject Headings for this publication:

Artificial intelligence -- Data processing.
Biologically-inspired computing.
Self-organizing systems.
Autonomous robots.