Graph composition in a graph grammar-based method for automata network evolution
作者： M.H. Luerssen , D.M.W. Powers
关键词:
摘要: The dynamics of neural and other automata networks are defined to a large extent by their topologies. Artificial evolution constitutes practical means which an optimal topology can be determined. Constructing grammar good graphs then deriving new from this facilitate process. following paper presents simple but novel method evolving hypergraph for purpose. Different strategies composing within framework evaluated on problems symbolic regression, time series approximation, networks. results favour selectively modular approach that connects nodes with the most similar, rather than identical, labels.
flinders.edu.au
dodo.com.au 参考文章(26)
Marc Toussaint, The evolution of genetic representations and modular neural adaptation ,(2004)
Servet Martínez, Eric Goles, Neural and Automata Networks: Dynamical Behavior and Applications ,(2011)
H. Kitnano, Designing Neural Networks Using Genetic Algorithms with Graph Generation System Complex Systems. ,vol. 4, ,(1990)
Martin H. Luerssen, David M. W. Powers, On the Artificial Evolution of Neural Graph Grammars ,(2003)
Martin H. Luerssen, Graph grammar encoding and evolution of automata networks ACSC '05 Proceedings of the Twenty-eighth Australasian conference on Computer Science - Volume 38. pp. 229- 238 ,(2005)
A. Habel, Hyperedge Replacement: Grammars and Languages ,(1992)
John R. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection ,(1992)
Peter M. Todd, Shailesh U. Hegde, Geoffrey F. Miller, Designing neural networks using genetic algorithms international conference on genetic algorithms. pp. 379- 384 ,(1989)
Conor Ryan, JJ Collins, Michael O Neill, Grammatical Evolution: Evolving Programs for an Arbitrary Language european conference on genetic programming. pp. 83- 96 ,(1998) , 10.1007/BFB0055930
Kalyanmoy Deb, Deb Kalyanmoy, Multi-Objective Optimization Using Evolutionary Algorithms ,(2001)