摘要: The global dynamics of automata networks (such as neural networks) are a function their topology and the choice used. Evolutionary methods can be applied to optimisation these parameters, but computational cost is prohibitive unless they operate on compact representation. Graph grammars provide such representation by allowing network regularities efficiently captured reused. We present system for encoding evolving collective hypergraph grammars, demonstrate its efficacy classical problems symbolic regression design architectures.
wardpowers.info 参考文章(32)
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)
Sara Silva, Jonas Almeida, Dynamic maximum tree depth: a simple technique for avoiding bloat in tree-based GP genetic and evolutionary computation conference. pp. 1776- 1787 ,(2003)
H. Kitnano, Designing Neural Networks Using Genetic Algorithms with Graph Generation System Complex Systems. ,vol. 4, ,(1990)
Sara Silva, Jonas Almeida, GPLAB A Genetic Programming Toolbox for MATLAB ,(2004)
Martin H. Luerssen, David M. W. Powers, On the Artificial Evolution of Neural Graph Grammars ,(2003)
C. Darwin, The Origin of Species by Means of Natural Selection ,(1859)
Julian F. Miller, Peter Thomson, A Developmental Method for Growing Graphs and Circuits Evolvable Systems: From Biology to Hardware. pp. 93- 104 ,(2003) , 10.1007/3-540-36553-2_9
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams, Learning representations by back-propagating errors Nature. ,vol. 323, pp. 696- 699 ,(1988) , 10.1038/323533A0
Darrell Whitley, V. Scott Gordon, Keith Mathias, Lamarckian Evolution, The Baldwin Effect and Function Optimization parallel problem solving from nature. pp. 6- 15 ,(1994) , 10.1007/3-540-58484-6_245