Investigation of ANN Model Containing One Hidden Layer for Predicting Compressive Strength of Concrete with Blast-Furnace Slag and Fly Ash

Table 5

Summary of different quality assessment criteria for the best ANN predictor using 24 neurons in the hidden layer, denoted as ANN-[8-24-1].

	RMSE	MAE	Err. mean	Err. Std	R^2
Training set	3.9474	2.9074	−0.0124	3.9496	0.9437
Testing set	4.4266	3.2971	0.1285	4.4306	0.9285