论文信息 - Mathematical analysis of crossover operator in genetic algorithms and its improved strategy

Mathematical analysis of crossover operator in genetic algorithms and its improved strategy

This paper analyzes two types of crossover ways( one-point crossover and uniform crossover) based on the choice theorem of optimal crossover point, and then proposes two new crossover ways that are called "circlering crossover" and "sufficient exchangmg" Computer simulation results demonstrate the validity of the improved strategy

Zhang Liang-Jie | Li Yan-Da | Mao Zhi-Hong

[1] James F. Frenzel,et al. Training product unit neural networks with genetic algorithms , 1993, IEEE Expert.

[2] John H. Holland,et al. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[3] Günter Rudolph,et al. Convergence analysis of canonical genetic algorithms , 1994, IEEE Trans. Neural Networks.

[4] John J. Grefenstette,et al. Optimization of Control Parameters for Genetic Algorithms , 1986, IEEE Transactions on Systems, Man, and Cybernetics.

[5] Y. Ikuno,et al. Application of an Improved Genetic Algorithm to the Learning of Neural Networks , 1994 .

[6] Hiroshi Nagahashi,et al. Structural Evolution of Neural Networks Having Arbitrary Connections by a Genetic Method , 1993 .