摘要
提出一种基于遗传程序设计算法(GPA)求解决策树结点的权值矢量,并根据树结点的 错误率与分割后的错误率减少量构造GP 决策树算法的方法。该方法不但可以求解出树结点的权值 矢量,同时也确定了GP 决策树的结构。实验结果表明,应用GP 决策树算法能够正确完成对趋势预 测模型的选择。
A approach to solving the weights' vector algorithm of GP-decision tree based on genetic programming algorithm was introduced,according to decrement of tree node error ratio and divided error ratio. Not only do solving the weights' vector of tree node, but also ascertaining the construct of two-member decision tree by using this approach. Experimental results show that the choice for trend forecasting models can be correctly finished by using GP-decision tree algorithm.
出处
《计算机应用》
CSCD
北大核心
2005年第4期739-741,共3页
journal of Computer Applications
基金
国家自然科学基金资助(60373083)
关键词
遗传程序设计算法
GP-决策树算法
模型选择
Genetic Programming Algorithm(GPA)
GP-decision tree algorithm
model choice
