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 |