Fitness first and fatherless crossover
Fitness first and fatherless crossover
复制标题
健身第一与无父交叉
DOI:
10.1145/3449726.3459437
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
Langdon W
中科院分区:
文献类型:
--
作者:
Langdon W
When programs are very large and fitness evaluation is fast (e.g. due to evaluating only a tiny fraction of the program) it can be efficient to evaluate fitness before creating the program, as only individuals with children need be created. The saving can be > 50% and even in highly converged populations, it savese-2= 13.5%.In GP crossover one child is created from two parents but the root donating parent (mum) contributes far more than the other (dad). The subtree from the father is usually small and can be extracted from each dad and saved before crossover. This gives single parent crossover, which when combined with fitness first, further reduces the number of crossovers. Even in the worst case the reduction is exp(-1) = 37 percent.With large trees, even in populations of similar fitness, eliminating bachelors and spinsters is feasible and can reduce both runtime and memory consumption. Storage in a (N) multi-threaded implementation for a population M is about 0.63M + N, compared to the usual M+2N, in practice saving ≥ 17%. We achieve 692 billion GP operations per second, 692 giga GPops, on an Intel i7-9800X 16 thread 3.8GHz desktop (CPU bandwidth 85 GByte/second).
DOI:
--
发表时间:
2020
期刊:
ACM SIGEVOlution
影响因子:
--
作者:
W. Langdon
通讯作者:
W. Langdon
DOI:
--
发表时间:
2019
期刊:
Artificial Life Conference Proceedings
影响因子:
--
作者:
W. Langdon;W. Banzhaf
通讯作者:
W. Banzhaf
DOI:
--
发表时间:
2021
期刊:
European Conference on Genetic Programming
影响因子:
--
作者:
W. Langdon
通讯作者:
W. Langdon