Table 4 Characteristics of the basic models.
From: Failure Mode Detection of Reinforced Concrete Shear Walls Using Ensemble Deep Neural Networks
Sub-model | 1 | 2 | 3 | 4 | 5 |
|---|---|---|---|---|---|
Number of neurons | |||||
Layer 1 | 40 | 25 | 40 | 25 | 20 |
Drop rate | 0.02 | 0.01 | 0.01 | – | – |
Layer 2 | 80 | 80 | 60 | 20 | 50 |
Drop rate | – | – | 0.01 | – | – |
Layer 3 | – | 20 | 60 | 80 | 30 |
Layer 4 | – | – | 15 | 80 | 60 |
Layer 5 | – | – | – | 40 | 80 |
Layer 6 | – | – | – | – | 25 |
Activation | Tanh | Tanh | Tanh | Tanh | Tanh |
Optimizer | Adam | Adam | Adam | Adam | Adam |
Learning rate | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 |
R2 score (test set) | 0.83 | 0.81 | 0.82 | 0.84 | 0.81 |