Table 4 Result of 10-fold cross validation of algorithms.

From: Passive determination of anisotropic compressive strength of 3D printed concrete using multiple neural networks enhanced with explainable machine learning (XML)

Mean Values

MLP

RBFNN

CNN

Training MAE

6.316

4.943

5.024

Validation MAE

7.034

6.299

5.952

Training \(\:{\text{R}}^{2}\)

0.934

0.950

0.950

Validation \(\:{\text{R}}^{2}\)

0.922

0.931

0.934

Back to article page