Adaptive Representations for Improving Evolvability, Parameter Control, and Parallelization of Gene Expression Programming

Table 1

Common experiment run parameters.

Parameter	Problem
	Symbolic Regression & Parameter Optimization	Classification
Selection method	Elitist Tournament	Elitist Tournament
Number of generations	100	175
Population size	100	75
Initial head size	5–15	5–15
Initial number of genes	1–10	1–10
One point recombination rate	0.5	0.5
Two point recombination rate	0.1	0.1
Gene recombination rate	0.1	0.1
Mutation rate	0.07	0.07
Minimum ACS mutation rate	0.05	0.05
IS transposition rate	0.1	0.1
RIS transposition rate	0.1	0.1
HIS transposition rate	0.1	0.1
Gene transposition rate	0.1	0.1
Function set	𝐹1	𝐹2
Linking function	+	+
K-Fold validation	10 folds	10 folds
Evolutionary Clients (Syrah)	31	31

𝐹₁={+,−,∗,/}, 𝐹₂={+,−,∗,/,sqrt,exp,sin,cos,tan,floor,ceiling,OR,AND,<,>,≤,≥,==,!=}.