Some Considerations on the Reason for Bloat

被引：64

作者：

W. Banzhaf

W. B. Langdon

机构：

[1] Dortmund University,Department of Computer Science

[2] University College,Computer Science

[3] London,undefined

来源：

Genetic Programming and Evolvable Machines | 2002年 / 3卷 / 1期

关键词：

genetic programming; linear genomes; effective fitness; neutral variations;

D O I：

10.1023/A:1014548204452

中图分类号：

学科分类号：

摘要：

A representation-less model for genetic programming is presented. The model is intended to examine the mechanisms that lead to bloat in genetic programming (GP). We discuss two hypotheses (“fitness causes bloat” and “neutral code is protective”) and perform simulations to examine the predictions deduced from these hypotheses. Our observation is that predictions from both hypotheses are realized in the simulated model.

引用

页码：81 / 91

页数：10

共 9 条

[1]

Brameier M.(2001)A comparison of linear genetic programming and neural networks in medical data mining IEEE Trans. Evolutionary Computation 5 17-26

[2]

Banzhaf W.(1999)Scaling of program tree fitness spaces Evolutionary Computation 7 399-428

[3]

Langdon W. B.(2000)Size fair and homologous tree crossover for tree GP Genetic Programming and Evolvable Machines 1 95-120

[4]

Langdon W. B.(2001)Exact schema theory for genetic programming and variable-length genetic algorithms with one-point crossover Genetic Programming and Evolvable Machines 2 123-163

[5]

Poli R.(2000)Effective fitness as an alternative paradigm for evolutionary computation I: General formalism Genetic Programming and Evolvable Machines 1 363-378

[6]

Stephens C.(2001)Effective fitness as an alternative paradigm for evolutionary computation II: Examples and applications Genetic Programming and Evolvable Machines 2 7-32

[7]

Mora Vargas J.(undefined)undefined undefined undefined undefined-undefined

[8]

Stephens C.(undefined)undefined undefined undefined undefined-undefined

[9]

Mora Vargas J.(undefined)undefined undefined undefined undefined-undefined

← 1 →