Muutke küpsiste eelistusi

Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies [Pehme köide]

, (Ecole Polytechnique Federale de Lausanne)
Teised raamatud teemal:
Teised raamatud teemal:
A comprehensive introduction to new approaches in artificial intelligence and robotics that are inspired by self-organizing biological processes and structures.

New approaches to artificial intelligence spring from the idea that intelligence emerges as much from cells, bodies, and societies as it does from evolution, development, and learning. Traditionally, artificial intelligence has been concerned with reproducing the abilities of human brains; newer approaches take inspiration from a wider range of biological structures that that are capable of autonomous self-organization. Examples of these new approaches include evolutionary computation and evolutionary electronics, artificial neural networks, immune systems, biorobotics, and swarm intelligence—to mention only a few. This book offers a comprehensive introduction to the emerging field of biologically inspired artificial intelligence that can be used as an upper-level text or as a reference for researchers. Each chapter presents computational approaches inspired by a different biological system; each begins with background information about the biological system and then proceeds to develop computational models that make use of biological concepts. The chapters cover evolutionary computation and electronics; cellular systems; neural systems, including neuromorphic engineering; developmental systems; immune systems; behavioral systems—including several approaches to robotics, including behavior-based, bio-mimetic, epigenetic, and evolutionary robots; and collective systems, including swarm robotics as well as cooperative and competitive co-evolving systems. Chapters end with a concluding overview and suggested reading.
Preface xi
Acknowledgments xiii
1 Evolutionary Systems
1(100)
1.1 Pillars of Evolutionary Theory
2(3)
1.2 The Genotype
5(8)
1.3 Artificial Evolution
13(3)
1.4 Genetic Representations
16(5)
1.5 Initial Population
21(1)
1.6 Fitness Functions
22(1)
1.7 Selection and Reproduction
23(3)
1.8 Genetic Operators
26(3)
1.9 Evolutionary Measures
29(4)
1.10 Types of Evolutionary Algorithms
33(4)
1.11 Schema Theory
37(2)
1.12 Human-Competitive Evolution
39(3)
1.13 Evolutionary Electronics
42(1)
1.14 Lessons from Evolutionary Electronics
43(2)
1.15 The Role of Abstraction
45(4)
1.16 Analog and Digital Circuits
49(4)
1.17 Extrinsic and Intrinsic Evolution
53(5)
1.18 Digital Design
58(4)
1.19 Evolutionary Digital Design
62(15)
1.20 Analog Design
77(2)
1.21 Evolutionary Analog Design
79(6)
1.22 Multiple Objectives and Constraints
85(5)
1.23 Design Verification
90(2)
1.24 Closing Remarks
92(5)
1.25 Suggested Readings
97(4)
2 Cellular Systems
101(62)
2.1 The Basic Ingredients
101(6)
2.2 Cellular Automata
107(3)
2.3 Modeling with Cellular Systems
110(8)
2.4 Some Classic Cellular Automata
118(6)
2.5 Other Cellular Systems
124(10)
2.6 Computation
134(4)
2.7 Artificial Life
138(7)
2.8 Complex Systems
145(8)
2.9 Analysis and Synthesis of Cellular Systems
153(6)
2.10 Closing Remarks
159(1)
2.11 Suggested Readings
160(3)
3 Neural Systems
163(106)
3.1 Biological Nervous Systems
167(8)
3.2 Artificial Neural Networks
175(2)
3.3 Neuron Models
177(12)
3.4 Architecture
189(2)
3.5 Signal Encoding
191(5)
3.6 Synaptic Plasticity
196(2)
3.7 Unsupervised Learning
198(21)
3.8 Supervised Learning
219(16)
3.9 Reinforcement Learning
235(3)
3.10 Evolution of Neural Networks
238(12)
3.11 Neural Hardware
250(6)
3.12 Hybrid Neural Systems
256(5)
3.13 Closing Remarks
261(4)
3.14 Suggested Readings
265(4)
4 Developmental Systems
269(66)
4.1 Potential Advantages of a Developmental Representation
270(2)
4.2 Rewriting Systems
272(24)
4.3 Synthesis of Developmental Systems
296(2)
4.4 Evolution and Development
298(1)
4.5 Defining Artificial Evolutionary Developmental Systems
299(2)
4.6 Evolutionary Rewriting Systems
301(9)
4.7 Evolutionary Developmental Programs
310(5)
4.8 Evolutionary Developmental Processes
315(17)
4.9 Closing Remarks
332(2)
4.10 Suggested Readings
334(1)
5 Immune Systems
335(64)
5.1 How Biological Immune Systems Work
337(16)
5.2 The Constituents of Biological Immune Systems
353(13)
5.3 Lessons for Artificial Immune Systems
366(7)
5.4 Algorithms and Applications
373(2)
5.5 Shape Space
375(9)
5.6 Negative Selection Algorithm
384(4)
5.7 Clonal Selection Algorithm
388(2)
5.8 Examples
390(5)
5.9 Closing Remarks
395(1)
5.10 Suggested Readings
396(3)
6 Behavioral Systems
399(116)
6.1 Behavior in Cognitive Science
400(3)
6.2 Behavior in Artificial Intelligence
403(4)
6.3 Behavior-Based Robotics
407(12)
6.4 Biological Inspiration for Robots
419(18)
6.5 Robots as Biological Models
437(12)
6.6 Robot Learning
449(11)
6.7 Evolution of Behavioral Systems
460(22)
6.8 Evolution and Learning in Behavioral Systems
482(12)
6.9 Evolution and Neural Development in Behavioral Systems
494(5)
6.10 Coevolution of Body and Control
499(5)
6.11 Toward Self-Reproduction
504(3)
6.12 Simulation and Reality
507(4)
6.13 Closing Remarks
511(2)
6.14 Suggested Readings
513(2)
7 Collective Systems
515(70)
7.1 Biological Self-Organization
516(8)
7.2 Particle Swarm Optimization
524(3)
7.3 Ant Colony Optimization
527(4)
7.4 Swarm Robotics
531(16)
7.5 Coevolutionary Dynamics: Biological Models
547(7)
7.6 Artificial Evolution of Competing Systems
554(18)
7.7 Artificial Evolution of Cooperation
572(9)
7.8 Closing Remarks
581(2)
7.9 Suggested Readings
583(2)
Conclusion 585(2)
References 587(64)
Index 651