Figure 17. The regression plot showing the predicted (output) and target (observed) values for validation dataset during validation stage of ANN model (RHA and A-7-5 and cement).
Figure 18 shows the training performance. Generally, the error reduces after more epochs of training, but might start to increase on the validation data set as the network starts overfitting the training data in the default setup, the training stops after six consecutive increases in validation error and the best performance is taken from the epoch with the lowest validation error [30].