Skip to main content

Advertisement

Table 7 Exploration of different ML algorithms in the prediction of DFT DM using the 75 most important descriptors obtained for model C

From: Machine learning for the prediction of molecular dipole moments obtained by density functional theory

ML MAE (D) R2/RMSE (D)
Training set
 SVM 0.531 0.819/0.783
 MLP 0.550 0.813/0.797
 RBF 0.561 0.811/0.801
Test set
 SVM 0.526 0.840/0.755
 MLP 0.531 0.836/0.763
 RBF 0.538 0.839/0.757
  1. Predictions for the training set were obtained with ten-fold cross-validation experiments