Skip to main content

Table 1 Parameter configuration in the LGP algorithm

From: SMILE: systems metabolomics using interpretable learning and evolution

Parameter Setting
Fitness function Accuracy score
Program initialization Random
Program initialization length [10, 40]
Max program length 300
Population size 800
Number of generations 240
Operator set +, -, x, \(\div\), exponent, \(if<\), \(if>\)
Constant set Random int from 1 - 10
Parent selection Tournament with size 8
Crossover probability 0.75
Micro-mutation probability 0.5
Macro-mutation probability 0.75
Random sampling Bootstrap without replacement