A comparison of matrix rewriting versus direct encoding for evolving neural networks
作者：
关键词:
摘要: The intuitive expectation is that the scheme used to encode neural network in chromosome should be critical success of evolving networks solve difficult problems. In 1990 Kitano published an encoding based on context-free parallel matrix rewriting. method allowed compact, finite, chromosomes grow potentially infinite size. Results were presented demonstrated superior evolutionary properties rewriting compared a simple direct encoding. authors present results contradict those findings, and demonstrate genetic algorithm (GA) using can find good individuals just as efficiently GA
sci-hub.se 参考文章(19)
Simon M. Lucas, Growing adaptive neural networks with graph grammars. the european symposium on artificial neural networks. ,(1995)
Egbert J. W. Boers, Herman Kuiper, Bart L. M. Happel, Ida G. Sprinkhuizen-Kuyper, Biological Metaphors In Designing Modular Artificial Neural Networks ICANN ’93. pp. 780- 780 ,(1993) , 10.1007/978-1-4471-2063-6_219
Simon M. Lucas, Evolving neural network learning behaviours with set-based chromosomes. the european symposium on artificial neural networks. ,(1996)
H. Kitnano, Designing Neural Networks Using Genetic Algorithms with Graph Generation System Complex Systems. ,vol. 4, ,(1990)
J. R. McDonnell, W. C. Page, D. E. Waagen, Neural Network Construction Using Evolutionary Search. Defense Technical Information Center. ,(1994) , 10.21236/ADA290862
L. Marti, Genetically generated neural networks. II. Searching for an optimal representation international joint conference on neural network. ,vol. 2, pp. 221- 226 ,(1992) , 10.1109/IJCNN.1992.227004
Frederic Gruau, Darrell Whitley, Larry Pyeatt, None, A comparison between cellular encoding and direct encoding for genetic neural networks Proceedings of the 1st annual conference on genetic programming. pp. 81- 89 ,(1996)
Byoung-Tak Zhang, H. Muhlenbein, Synthesis of sigma-pi neural networks by the breeder genetic programming world congress on computational intelligence. pp. 318- 323 ,(1994) , 10.1109/ICEC.1994.349933
Hiroaki Kitano, Neurogenetic learning: an integrated method of designing and training neural networks using genetic algorithms Physica D: Nonlinear Phenomena. ,vol. 75, pp. 225- 238 ,(1994) , 10.1016/0167-2789(94)90285-2
Hiroaki Kitano, A simple model of neurogenesis and cell differentiation based on evolutionary large-scale chaos Artificial Life. ,vol. 2, pp. 79- 99 ,(1995) , 10.1162/ARTL.1994.2.79