How do evolved digital logic circuits generalise successfully?

Authors:
Simon McGregor
Affiliations:
Centre for Computational, Neuroscience and Robotics, UK
Venue:
ECAL'05 Proceedings of the 8th European conference on Advances in Artificial Life
Year:
2005

Citing 6
Cited 0

Genetic programming II: automatic discovery of reusable programs

Genetic programming II: automatic discovery of reusable programs
An introduction to Kolmogorov complexity and its applications (2nd ed.)

An introduction to Kolmogorov complexity and its applications (2nd ed.)
The genetic algorithm as a discovery engine: strange circuits and new principles

Creative evolutionary systems
An Introduction to Genetic Algorithms

An Introduction to Genetic Algorithms
Aspects of Digital Evolution: Geometry and Learning

ICES '98 Proceedings of the Second International Conference on Evolvable Systems: From Biology to Hardware
The Test Vector Problem and Limitations to Evolving Digital Circuits

EH '00 Proceedings of the 2nd NASA/DoD workshop on Evolvable Hardware

Quantified Score

Hi-index	0.00

Visualization

Abstract

Contrary to indications made by prior researchers, digital logic circuits designed by artificial evolution to perform binary arithmetic tasks can generalise on inputs which were not seen during evolution. This phenomenon is demonstrated experimentally and speculatively explained in terms of the regular structure of binary arithmetic tasks and the nonoptimality of random circuits. This explanation rests on an assumption that evolution is relatively unbiased in its exploration of circuit space. Further experimental data is provided to support the proposed explanation.