摘要
对遗传程序设计(GP)算法中的适应度评价函数光滑拟合问题进行了研究,结合LAM(LinearAssociationMemory)和HJ(Hook和Jeevs)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。提出了一种选择调整参数的新方法,同时,给出了一个数学例子,并与广义交叉实验B—样条函数仿真比较验证。
The smooth fitting problem of fitness evalutation function under the genetic programming(GP) algorithm was discussed. To reduce the computational cost required for evaluating the fitness value of GP trees, numerical weights of GP trees were 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, a novel method for choosing the regularization parameter was presented. One numerical example was given with the comparison of generalized cross-validation (GCV) B-splines.
出处
《计算机应用》
CSCD
北大核心
2005年第6期1330-1333,共4页
journal of Computer Applications
基金
国家自然科学基金资助项目(60373083)
