Genetic programming convergence
Genetic programming convergence
复制标题
DOI：
10.1007/s10710-021-09405-9
复制
发表时间：
2021-08-30
影响因子：
2.6
通讯作者：
Langdon, W. B.
中科院分区：
文献类型：
--
作者：
Langdon, W. B.
我们研究了数千代 GP 浮点连续域符号回归的基因型和表型收敛。我们测量了整个群体的子树适合度变化，结果表明在许多情况下子树适合度都在下降。在根节点附近不断扩大的区域内，基因操作码和函数评估值都相同或几乎相同。自下而上（从叶到根）的分析表明，语法和语义（包括熵）的相似性都从最外层的节点开始扩展。尽管存在大面积的零变化，但适应性仍在继续发展，而接近零的交叉干扰表明，在现有内存使用范围内，GP 系统得到了改进。
We study both genotypic and phenotypic convergence in GP floating point continuous domain symbolic regression over thousands of generations. Subtree fitness variation across the population is measured and shown in many cases to fall. In an expanding region about the root node, both genetic opcodes and function evaluation values are identical or nearly identical. Bottom up (leaf to root) analysis shows both syntactic and semantic (including entropy) similarity expand from the outermost node. Despite large regions of zero variation, fitness continues to evolve and near zero crossover disruption suggests improved GP systems within existing memory use.