Dynamic page based crossover in linear genetic programming

被引：39

作者：

Heywood, MI ^{[1
]}

Zincir-Heywood, AN ^{[1
]}

机构：

[1] Dalhousie Univ, Fac Comp Sci, Halifax, NS B3H 1W5, Canada

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS | 2002年 / 32卷 / 03期

关键词：

benchmarking; genetic programming; homologous crossover; linear structures;

D O I：

10.1109/TSMCB.2002.999814

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Page-based linear genetic programming (GP) is proposed in which individuals am described in terms of a number of pages. Pages are expressed in terms of a fixed number of instructions,which Is constant for all individuals in the population. Pairwise crossover results in the swapping of single pages, and thus, individuals are of a fixed number of instructions. Head-to-head comparison with Tree-structured GP and block-based linear GP indicates that the page-based approach evolves succinct solutions without penalizing generalization ability.

引用

页码：380 / 388

页数：9

共 19 条

[1]

*AIML TM TECHN, DISC 2 0

[2]

ANGELINE PJ, 1996, ADV GENETIC PROGRAMM, V2, P1

[3]

Chellapilla K., 1997, IEEE Transactions on Evolutionary Computation, V1, P209, DOI 10.1109/4235.661552

[4]

Cramer N.L., 1985, Proceedings of the First International Conference on Genetic Algorithms and their Applications (ICGA'85), P183, DOI 10.4324/9781315799674-19

[5]

Friedrich H., 1958, Zoology of Iceland, V2, P1

[6]

Heywood MI, 2000, IEEE SYS MAN CYBERN, P3823, DOI 10.1109/ICSMC.2000.886606

[7]

Heywood MI, 2000, LECT NOTES COMPUT SC, V1802, P44

[8]

Holland J. H, 1998, ADAPTATION NATURAL A

[9]

Huelsbergen L., 1996, Genetic Programming. Proceedings of the First Annual Conference 1996, P315

[10]

Koza J.R., 1994, Genetic Programming II: Automatic Discovery of Reusable Programs

← 1 2 →