Abstract:
In earlier work we predicted program size would grow in the limit at a quadratic rate and up to fifty generations we measured bloat O(generations 1:2\Gamma1:5 ). On two simple benchmarks we test the prediction of bloat O(generations 2:0 ) up to generation 600. In continuous problems the limit of quadratic growth is reached but convergence in the discrete case limits growth in size. Measurements indicate subtree crossover ceases to be disruptive with large programs (1,000,000) and the population effectively converges (even though variety is near unity). Depending upon implementation, we predict run time O(no. generations 2:0\Gamma3:0 ) and memory O(no. generations 1:0\Gamma2:0 ). 1 INTRODUCTION It has been known for some time that programs within GP populations tend to rapidly increase in size as the population evolves [ Koza, 1992, Altenberg, 1994, Tackett, 1994, Blickle and Thiele, 1994, Nordin and Banzhaf, 1995, Nordin, 1997, McPhee and Miller, 1995, Langdon,...
Citations
|
1921
|
Genetic Programming I : On the Programming of Computers by Means of Natural Selection
– Koza
- 1992
|
|
116
|
Complexity compression and evolution
– Nordin, Banzhaf
- 1995
|
|
78
|
Explicitly Defined Introns and Destructive Crossover in Genetic Programming
– Nordin, Francone
- 1996
|
|
73
|
Code growth in genetic programming
– Soule, Foster, et al.
- 1996
|
|
66
|
The average height of binary trees and other simple trees
– Flajolet, Odlyzko
- 1982
|
|
63
|
The Evolution of Size and Shape
– Langdon, Soule, et al.
- 1999
|
|
60
|
Balancing accuracy and parsimony in genetic programming
– Zhang, Mühlenbein
- 1995
|
|
57
|
Size fair and homologous tree genetic programming crossovers. Genetic Programming and Evolvable Machines
– Langdon
- 2000
|
|
57
|
Analysis of complexity drift in genetic programming
– Rosca
- 1997
|
|
54
|
Accurate Replication in Genetic Programming
– McPhee, Miller
- 1995
|
|
52
|
Evolutionary Program Induction of Binary Machine Code and Its Application
– Nordin
- 1997
|
|
51
|
Fitness causes bloat
– Langdon, Poli
- 1997
|
|
41
|
Pygmies and civil servants
– Ryan
- 1994
|
|
26
|
An analysis of the MAX problem in genetic programming
– Langdon, Poli
- 1997
|
|
26
|
Code Size and Depth Flows in Genetic Programming
– Soule, Foster
- 1997
|
|
25
|
The evolution of size in variable length representations
– Langdon
- 1998
|
|
24
|
On the use of a directed acyclic graph to represent a population of computer programs
– Handley
- 1994
|
|
24
|
the Genetic Construction of Computer Programs
– Recombination
- 1994
|
|
23
|
Emergent phenomena in genetic programming
– Altenberg
- 1994
|
|
21
|
Removal bias: a new cause of code growth in tree based evolutionary programming
– Soule, Foster
- 1998
|
|
19
|
An Investigation of Supervised Learning in Genetic Programming
– Gathercole
- 1998
|
|
18
|
Sub-Machine-Code Genetic Programming
– Poll, Langdon
- 1999
|
|
17
|
Evolving compact solutions in genetic programming: A case study
– Blickle
- 1996
|
|
16
|
Blickle and Lothar Thiele. Genetic programming and redundancy
– Tobias
- 1994
|
|
14
|
Crossover Causes Bloat
– Angeline, Subtree
- 1998
|
|
14
|
Complexity drift in evolutionary computation with tree representations
– Rosca, Ballard
- 1996
|
|
12
|
de Garis, and Taisuke Sato. Genetic programming using a minimum description length principle
– Iba, Hugo
- 1994
|
|
10
|
Scaling of program tree fitness spaces
– Langdon
- 1999
|
|
8
|
Recombinative hill-climbing: A stronger search method for genetic programming
– Hooper, Flann, et al.
- 1997
|
|
5
|
Seeding GP populations
– Langdon, Nordin
- 2000
|
