| Parameters | FNN method with Backpropagation | DNN Method |
|---|---|---|
| Activation function | Sigmoid | Sigmoid |
| Learning rate | 0.6 | 0.1 |
| Momentum | 0.4 | N/A |
| Maximum number of training iterations | 4 x 106 | 4 x 106 |
| Number of hidden layers | 0 | 3 |
| Weight function | N/A | Xavier |
| Seed value | N/A | 6 |
| Backpropagation | Yes | Yes |
| Regularization | N/A | L2 |