Table 3 Performance of the deep neural networks (DNNs).

From: A machine learning enabled hybrid optimization framework for efficient coarse-graining of a model polymer

DNN

MAE (training)

MAE (5-fold validation)

MAE (resting)

Training time (s)

  

Mean

Standard deviation

  

Bonded potentiala

0.025

0.03

0.005

0.028

1539

Angle potentiala

0.026

0.034

0.004

0.030

963

Density

0.029

0.033

0.002

0.036

1952

  1. aThe DNNs of bonded and angle potentials present the aggregated mean absolute errors.
Back to article page