Skip to main content

Table 3 List of hyperparameters tuned during cross-validation

From: The effect of preprocessing filters on predictive performance in radiomics

Classifier Hyperparameter
Logistic regression C in 2^{-6, -4, -2, 0, 2, 4, 6}
Neural networks Three layers with each 4, 16, or 64 neurons
Random forest Number of estimators 50, 125, or 250
Radial basis function
Sector vector machine
C in 2^{-6, -4, -2, 0, 2, 4, 6}, gamma was set to auto
  1. The remaining hyperparameters were left at their default