Research on Smooth Fitting and Regularization Parameter under the Fitness Function of Genetic Programming Algorithm
-
摘要: 研究了遗传程序设计(GP)算法中适应度函数的光滑拟合问题,结合LAMs(Linear association memorys)方法和HJ(Hook和Jeevs)方法两种方法,估计GP树数值权值,以减少GP树适应度值评价的计算代价.光滑拟合的好坏关键取决于调整参数的选择.提出了一种选择调整参数的新方法,同时,给出了两个数学例子,并与广义交叉实验B-样条函数仿真比较验证.
-
关键词:
- 自遗传程序设计(GP) /
- 适应度函数 /
- 光滑拟合 /
- 调整参数
Abstract: This paper deals with the smooth fitting problem under the genetic programming (GP) algorithm. To reduce the computational cost required for evaluating the fitness value of GP trees, numerical weights of GP trees are estimated by adopting both linear associative memories (LAM) and the Hook and Jeeves (HJ) method. The quality of smooth fitting is critically dependent on the choice of the regularization parameter. So, we present a novel method for choosing the regularization parameter. Two numerical examples are given with comparison to the generalized cross-validation (GCV) B-splines.-
Key words:
- Genetic programming /
- fitness function /
- smooth fitting /
- regularization parameter
-
点击查看大图
计量
- 文章访问数: 3365
- HTML全文浏览量: 167
- PDF下载量: 1793
- 被引次数: 0
下载:
