Prediction of Compressive Strength Behavior of Ground Bottom Ash Concrete by an Artificial Neural Network

Table 8

The parameter setting used in the optimal ANN models.

Parameter setting	Best model
Number of input layer units	4
Number of first hidden layer units	6
Number of second hidden layer units	1
Number of output layer units	1
Number of epochs	5,500
Training algorithm	BR
Activation function in first hidden layer	Log-sigmoid
Activation function in second hidden layer	Tan-sigmoid
Activation function in output layer	Purelin
Network’s performance	sse