当前位置: X-MOL 学术Appl. Soft Comput. › 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.)
An evolvable hardware method based on elite Partheno-Genetic Algorithm
Applied Soft Computing ( IF 7.2 ) Pub Date : 2021-09-17 , DOI: 10.1016/j.asoc.2021.107904
Lijun Liu 1 , Tao Wang 1
Affiliation  

Aiming at the shortcomings of traditional genetic algorithm (GA) in the overall evolution of hardware, such as slow speed and small scale, a method of evolvable hardware (EHW) based on elite Partheno-Genetic Algorithm (PGA) is proposed. To improve the evolution efficiency of EHW, the number of chromosomes is reduced, the length of the chromosome is increased, the elite node chain is reserved, and the connection relationship of non-elite nodes is adjusted. The experimental results show that: compared with the existing literature, the evolution speed is increased 144 times on average, the overall scale of evolution is increased 74.7 times, and the evolution efficiency is significantly improved.



中文翻译:

一种基于精英孤雌遗传算法的可进化硬件方法

针对传统遗传算法(GA)在硬件整体进化速度慢、规模小等缺点,提出了一种基于精英孤雌遗传算法(PGA)的硬件可进化算法(EHW)。为了提高EHW的进化效率,减少染色体数量,增加染色体长度,保留精英节点链,调整非精英节点的连接关系。实验结果表明:与现有文献相比,进化速度平均提高144倍,整体进化规模提高74.7倍,进化效率显着提高。

更新日期:2021-09-27
down
wechat
bug