Towards Evolvable Hardware: the Evolutionary Engineering Approach (Lecture Notes in Computer Science / Lecture Notes in Artificial Intelligence)

Evolutionary computing, inspired by the biological world, is one of the emergent technologies of our time. Being essentially a software activity, it has been successfully applied, e.g. for optimization and machine learning in various areas. The tremendous increase in computational power and, more recently, the appearance of a new generation of programmable logic devices allow for a new approach to designing computing machines inspired by biological models: it is now possible to make the hardware itself evolve. This book is based on a workshop on evolvable hardware, held in Lausanne, Switzerland, in October 1995. It reports the state of the art of research in this field and presents two introductory chapters, written with the novice reader in mind. Field programmable gate array (FPGA) circuits.- Evolutionary algorithms.- Artificial cellular development in optimization and compilation.- CAM-Brain the evolutionary engineering of a billion neuron artificial brain by 2001 which grows/evolves at electronic speeds inside a cellular automata machine (CAM).- Morphogenesis for evolvable systems.- Evolvable Hardware and its application to pattern recognition and fault-tolerant systems.- Unconstrained evolution and hard consequences.- Embryonics: The birth of synthetic life.- Embryonics: A new family of coarse-grained field-programmable gate array with self-repair and self-reproducing properties.- Evolution and mobile autonomous robotics.- Development and evolution of hardware behaviors.