Predicting Shear Capacity of FRP-Reinforced Concrete Beams without Stirrups by Artificial Neural Networks, Gene Expression Programming, and Regression Analysis

Table 3

Parameters used in the GEP Model.

Parameters	Values
Number of chromosomes	30–500
Head size	3, 5, 8
Number of genes	2, 3, 4
Linking function	Multiplication
Function set	+, −, /, ∗, abs, tanh, x^2, x^1/2, x^1/3, x^1/5, …
Generation without changes	2000
Number of tries	12
Maximum complexity	10
Fitness function	RMSE
Mutation	0.044
Inversion	0.1
One-point recombination	0.3
Two-point recombination	0.3
Gene recombination	0.1
Gene transposition	0.1
IS transposition	0.1
RIS transposition	0.1
Data type	Floating point
Constants per gene	10