Graph grammars for evolutionary 3D design
Created by W.Langdon from
gp-bibliography.bib Revision:1.8051
- @Article{McDermott:2013:GPEM,
-
author = "James McDermott",
-
title = "Graph grammars for evolutionary {3D} design",
-
journal = "Genetic Programming and Evolvable Machines",
-
year = "2013",
-
volume = "14",
-
number = "3",
-
pages = "369--393",
-
month = sep,
-
note = "Special issue on biologically inspired music, sound,
art and design",
-
keywords = "genetic algorithms, genetic programming, Grammatical
evolution, Graph grammars, 3D design, Indirect
representations",
-
ISSN = "1389-2576",
-
DOI = "doi:10.1007/s10710-013-9190-0",
-
size = "25 pages",
-
abstract = "A new interactive evolutionary 3D design system is
presented. The representation is based on graph
grammars, a fascinating and powerful formalism in which
nodes and edges are iteratively rewritten by rules
analogous to those of context-free grammars and shape
grammars. The nodes of the resulting derived graph are
labelled with Euclidean coordinates: therefore the
graph fully represents a 3D beam design. Results from
user-guided runs are presented, demonstrating the
flexibility of the representation. Comparison with
results using an alternative graph representation
demonstrates that the graph grammar search space is
more rich in organised designs. A set of numerical
features are defined over designs. They are shown to be
effective in distinguishing between the designs
produced by the two representations, and between
designs labelled by users as good or bad. The features
allow the definition of a non-interactive fitness
function in terms of proximity to target feature
vectors. In non-interactive experiments with this
fitness function, the graph grammar representation
out-performs the alternative graph representation, and
evolution out-performs random search.",
-
notes = "This paper is an expanded and improved version of
Graph Grammars as a Representation for Interactive
Evolutionary 3D Design, presented at EvoMUSART, Malaga,
Spain, 2012, \cite{McDermott:2012:EvoMUSART}",
- }
Genetic Programming entries for
James McDermott
Citations