From: Prediction of the hot asphalt mix properties using deep neural networks
 | Optimum ANN for every output | R-value | Optimum ANN for all predictions | R-value | R-difference | ||||
---|---|---|---|---|---|---|---|---|---|
Hidden layers | Neurons/layer | Activation function | Hidden layers | Neurons/layer | Activation function | ||||
OAC | 3 | 16 | Logistic | 0.909 | 2 | 11 | Linear | 0.841 | 0.068 |
Stability | 3 | 9 | Tanh | 0.795 | 0.753 | 0.042 | |||
Flow | 2 | 15 | Logistic | 0.528 | 0.512 | 0.016 | |||
Density | 2 | 11 | Linear | 0.653 | 0.653 | 0 | |||
AV | 4 | 8 | Tanh | 0.768 | 0.714 | 0.054 | |||
VMA | 4 | 7 | Tanh | 0.657 | 0.37 | 0.287 |