摘要
传统的数据建模方法 ,需要利用统计学和人工智能技术对数据进行探索性分析 ,操作者必须掌握大量的先验知识。将遗传程序设计 (GP)和遗传算法 (GA)应用到数据建模中 ,实现模型的自动获取。试验结果表明 ,在遗传操作中执行子树变异操作 ,将性能好的模型结构引入到进化中 。
In traditional data modeling, a lot of prior knowledge is needed to get the result by means of statistics and artificial intelligence technology. The application of Genetic Programming (GP) and Genetic Algorithm (GA) could make the automation of model possible. Experimental result shows that the convergent efficiency of Genetic Programming could be improved if subtree mutation is conducted and the models with the best fitness are brought into the evolution.
出处
《数理统计与管理》
CSSCI
北大核心
2001年第4期53-57,共5页
Journal of Applied Statistics and Management
