Table III.
Parameter | Value |
---|---|
Hidden Layers | 5 |
Layer Width | 170 |
Learning Rate | 1.1 × 10−3 |
Learning Rate Decay | 4.1 × 10−8 |
Dropout Probability | 4.4 × 10−4 |
Weight Initialization | He Normal |
Parameter | Value |
---|---|
Hidden Layers | 5 |
Layer Width | 170 |
Learning Rate | 1.1 × 10−3 |
Learning Rate Decay | 4.1 × 10−8 |
Dropout Probability | 4.4 × 10−4 |
Weight Initialization | He Normal |