Table 1 Root mean squared errors and R2 scores of the validation set by using regression models.

From: Simulation acceleration for transmittance of electromagnetic waves in 2D slit arrays using deep learning

Model

RMSE

R2 score

Train

Validation

Train

Validation

Convolutional neural network (CNN)

0.0364

0.0623

0.9496

0.8594

Multilayer perceptron (MLP)

0.0630

0.0845

0.8485

0.7411

Random forest

0.0416

0.0772

0.9372

0.7825

Extra tree

0.0292

0.0844

0.9693

0.7418

  1. Extra Tree best-performed in the training set, but CNN performed the best in the validation set.
Back to article page