Advertisement

Introduction

  • Adrian Thompson
Part of the Distinguished Dissertations book series (DISTDISS)

Abstract

There exist reconfigurable VLSI1 silicon chips for which the behaviours and interconnections of the constituent electronic primitives can be repeatedly changed. Artificial evolution can be used to derive a configuration causing the device to exhibit a pre-specified desired behaviour, without the intervention of a human designer. This book will argue that if, during evolution, each new variant configuration is assigned its fitness score according to the behaviour it induces in the real reconfigurable hardware, then evolution can be allowed to explore new kinds of circuits that are not within the scope of conventional design methods.

Keywords

Silicon Chip Fitness Score Hardware Evolution Artificial Evolution Reconfigurable Hardware 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    VLSI = Very Large Scale Integration.Google Scholar
  2. 2.
    It is possible to attack this distinction, but it seems mote useful to retain it. Reconfiguration and programming are two different viewpoints, which should be adopted appropriately for the system in question.Google Scholar
  3. 3.
    The use of the word ‘phenotype ‘to refer to behaviour (Dawkms, 1990) can be useful in other discussions of hardware evolution (Harvey & Thompson, 1997), but here it means the circuit itself.Google Scholar

Copyright information

© Springer-Verlag London Limited 1998

Authors and Affiliations

  • Adrian Thompson
    • 1
  1. 1.School of Cognitive and Computing SciencesUniversity of SussexFalmerUK

Personalised recommendations