Graph composition in a graph grammar-based method for automata network evolution

Author

Luerssen, Martin H. ; Powers, David M W

Author_Institution

Sch. of Informatics & Eng., Flinders Univ. of South Australia, Adelaide, SA, Australia

Volume

2

fYear

2005

fDate

2-5 Sept. 2005

Firstpage

1653

Abstract

The dynamics of neural and other automata networks are defined to a large extent by their topologies. Artificial evolution constitutes a practical means by which an optimal topology can be determined. Constructing a grammar of good graphs and then deriving new graphs from this grammar can facilitate this process. The following paper presents a simple but novel method of evolving a hypergraph grammar for this purpose. Different strategies for composing graphs within this framework are evaluated on problems of symbolic regression, time series approximation, and neural networks. The results favour a selectively modular approach that connects nodes with the most similar, rather than identical, labels.

Keywords

automata theory; graph grammars; artificial evolution; automata network evolution; graph composition; graph grammar; hypergraph grammar; neural networks; symbolic regression; time series approximation; Australia; Automata; Biological information theory; Biological system modeling; Computational modeling; Encoding; Evolution (biology); Informatics; Intelligent networks; Network topology;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation, 2005. The 2005 IEEE Congress on

Print_ISBN

0-7803-9363-5

Type

conf

DOI

10.1109/CEC.2005.1554887

Filename

1554887