An evolvability-enhanced artificial embryogeny for generating network structures

Authors:
Hidenori Komatsu;Yasuhiro Hashimoto;Yu Chen;Hirotada Ohashi
Affiliations:
Central Research Institute of Electric Power Industry, Iwado Kita, Komae City, Japan;University of Tokyo, Bunkyo-ku, Tokyo, Japan;University of Tokyo, Bunkyo-ku, Tokyo, Japan;University of Tokyo, Bunkyo-ku, Tokyo, Japan
Venue:
Proceedings of the 10th annual conference on Genetic and evolutionary computation
Year:
2008

Citing 5
Cited 1

Creating high-level components with a generative representation for body-brain evolution

Artificial Life
A Taxonomy for artificial embryogeny

Artificial Life
How artificial ontogenies can retard evolution

GECCO '05 Proceedings of the 7th annual workshop on Genetic and evolutionary computation
Evolving spring-mass models: a test-bed for graph encoding schemes

CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02
Environment as a spatial constraint on the growth of structural form

Proceedings of the 9th annual conference on Genetic and evolutionary computation

Co-evolution of morphology and control of soft-bodied multicellular animats

Proceedings of the 14th annual conference on Genetic and evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Existing Artificial Embryogeny (AE) models are insufficient to generate a network structure because the possible links are limited to those connecting nodes with their predefined neighbors. We propose a novel network generating AE model capable of generating links connected to predefined neighbors as well those to non-neighbors. This mechanism provides additional flexibility in phenotypes than existing AE models. Our AE model also incorporates a heterogeneous mutation mechanism to accelerate the convergence to a high fitness value or enhance the evolvability. We conduct experiments to generate a typical 2D grid pattern as well as a robot with a network structure consisting of masses, springs and muscles. In both tasks, results show that our AE model has higher evolvability, sufficient to search a larger space than that of conventional AE models bounded by local neighborhood relationships.