1. Introduction.- 1.1 Topic.- 1.2 Hardware Evolution.- 1.2.1 An Example of Reconfigurable Hardware.- 1.2.2 Evolving the Circuit Configuration.- 1.2.3 Intrinsic/Extrinsic.- 1.3 Motivation.- 1.4 The Thesis.- 2. Context.- 2.1 Inspiration.- 2.1.1 Mead et al.: Analog neural VLSI.- 2.1.2 Pulse-stream Neural Networks.- 2.1.3 Other Neural Hardware.- 2.1.4 Reconfigurable Hardware.- 2.1.5 Self-Timed Digital Design.- 2.1.6 Analogies with Software: Ray's Tierra.- 2.1.7 A Dynamical Systems Perspective.- 2.2 Evolutionary Algorithms for Electronic Design: Other approaches.- 2.2.1 ETL.- 2.2.2 deGaris.- 2.2.3 EPFL & CSEM: 'Embryonics'.- 2.2.4 A Sophisticated Extrinsic Approach: Hemmi et al.- 2.2.5 Evolving Analogue Circuits.- 2.2.6 A Silicon Neuromorph - The First Intrinsic Hardware Evolution?.- 2.2.7 Loosely Related Evolutionary Hardware Projects.- 2.3 Multi-Criteria EAs: Area, Power, Speed and Testability.- 2.4 A Philosophy of Artificial Evolutionx.- 2.4.1 Domain Knowledge, Morphogenesis, Encoding Schemes and Evolvability.- 2.4.2 Species Adaptation Genetic Algorithms (SAGA).- 2.5 The Position of this Book Within the Field.- 3. Unconstrained Structure and Dynamics.- 3.1 The Relationship Between Intrinsic Hardware Evolution and Conventional Design Techniques.- 3.2 Unconstrained Structure.- 3.3 Unconstrained Dynamics.- 3.3.1 Unconstrained Evolutionary Manipulation of Timescales I: Simulation study.- 3.3.2 II: Using a real FPGA.- 3.3.3 A Showpiece for Unconstrained Dynamics: An Evolved Hardware Sensorimotor Control Structure.- 3.4 The Relationship Between Intrinsic Hardware Evolution and Natural Evolution.- 4. Parsimony and Fault Tolerance.- 4.1 Insensitivity to Genetic Mutations.- 4.2 Engineering Consequences of Mutation-Insensitivity.- 4.3 Explicitly Specifying Fault-Tolerance Requirements.- 4.4 Adaptation to Faults.- 4.5 Fault Tolerance Through Redundancy.- 4.6 Summary.- 5. Demonstration.- 5.1 The Experiment.- 5.2 Results.- 5.3 Analysis.- 5.4 Interpretation.- 6. Future Work.- 6.1 Engineering Tolerances.- 6.2 Applications.- 7. Conclusion.- Appendix A. Circuit Diagram of the DSM Evolvable Hardware Robot Controller.- Appendix B. Details of the Simulations used in the 'Mr Chips' Robot Experiment.- B.1 The Motor Model.- B.2 The Movement Model.- B.3 The Sonar Model.- References.
Evolution through natural selection has been going on for a very long time. Evolution through artificial selection has been practiced by humans for a large part of our history, in the breeding of plants and livestock. Artificial evolution, where we evolve an artifact through artificial selection, has been around since electronic computers became common: about 30 years. Right from the beginning, people have suggested using artificial evolution to design electronics automatically.l Only recently, though, have suitable re configurable silicon chips become available that make it easy for artificial evolution to work with a real, physical, electronic medium: before them, ex periments had to be done entirely in software simulations. Early research concentrated on the potential applications opened-up by the raw speed ad vantage of dedicated digital hardware over software simulation on a general purpose computer. This book is an attempt to show that there is more to it than that. In fact, a radically new viewpoint is possible, with fascinating consequences. This book was written as a doctoral thesis, submitted in September 1996. As such, it was a rather daring exercise in ruthless brevity. Believing that the contribution I had to make was essentially a simple one, I resisted being drawn into peripheral discussions. In the places where I deliberately drop a subject, this implies neither that it's not interesting, nor that it's not relevant: just that it's not a crucial part of the tale I want to tell here.