当前位置:
X-MOL 学术
›
Genet. Program. Evolvable Mach.
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Horizontal gene transfer for recombining graphs
Genetic Programming and Evolvable Machines ( IF 2.6 ) Pub Date : 2020-02-03 , DOI: 10.1007/s10710-020-09378-1 Timothy Atkinson , Detlef Plump , Susan Stepney
Genetic Programming and Evolvable Machines ( IF 2.6 ) Pub Date : 2020-02-03 , DOI: 10.1007/s10710-020-09378-1 Timothy Atkinson , Detlef Plump , Susan Stepney
We introduce a form of neutral horizontal gene transfer (HGT) to evolving graphs by graph programming (EGGP). We introduce the $$\mu \times \lambda$$ μ × λ evolutionary algorithm (EA), where $$\mu$$ μ parents each produce $$\lambda$$ λ children who compete only with their parents. HGT events then copy the entire active component of one surviving parent into the inactive component of another parent, exchanging genetic information without reproduction. Experimental results from symbolic regression problems show that the introduction of the $$\mu \times \lambda$$ μ × λ EA and HGT events improve the performance of EGGP. Comparisons with genetic programming and Cartesian genetic programming strongly favour our proposed approach. We also investigate the effect of using HGT events in neuroevolution tasks. We again find that the introduction of HGT improves the performance of EGGP, demonstrating that HGT is an effective cross-domain mechanism for recombining graphs.
中文翻译:
用于重组图的水平基因转移
我们通过图编程(EGGP)向进化图引入了一种中性水平基因转移(HGT)形式。我们介绍了 $$\mu\times\lambda$$ μ × λ 进化算法(EA),其中 $$\mu$$ μ 父母每个都会产生 $$\lambda$$ λ 个孩子,这些孩子只与他们的父母竞争。HGT 事件然后将一个幸存亲本的整个活性成分复制到另一个亲本的非活性成分中,无需繁殖即可交换遗传信息。符号回归问题的实验结果表明,$$\mu\times\lambda$$ μ × λ EA 和 HGT 事件的引入提高了 EGGP 的性能。与遗传编程和笛卡尔遗传编程的比较强烈支持我们提出的方法。我们还研究了在神经进化任务中使用 HGT 事件的效果。
更新日期:2020-02-03
中文翻译:
用于重组图的水平基因转移
我们通过图编程(EGGP)向进化图引入了一种中性水平基因转移(HGT)形式。我们介绍了 $$\mu\times\lambda$$ μ × λ 进化算法(EA),其中 $$\mu$$ μ 父母每个都会产生 $$\lambda$$ λ 个孩子,这些孩子只与他们的父母竞争。HGT 事件然后将一个幸存亲本的整个活性成分复制到另一个亲本的非活性成分中,无需繁殖即可交换遗传信息。符号回归问题的实验结果表明,$$\mu\times\lambda$$ μ × λ EA 和 HGT 事件的引入提高了 EGGP 的性能。与遗传编程和笛卡尔遗传编程的比较强烈支持我们提出的方法。我们还研究了在神经进化任务中使用 HGT 事件的效果。