Table 1 Procedures of batch normalization
From: A robust modulation classification method using convolutional neural networks
Input: B, γ, β | |
|---|---|
Output: y={y1,y2,...,ym} | |
1. | Calculate the mean and variance value of B: |
| Â | \(\mu _{B}=\frac {1}{m}\sum _{i=1}^{m}x_{i},\) |
| Â | \(\sigma _{B}^{2}=\frac {1}{m}\sum _{i=1}^{m}(x_{i}-\mu _{B})^{2}\) |
2. | Normalize |
| Â | \(\hat {x_{i}}=\frac {x_{i}-\mu _{B}}{\sqrt {\sigma _{B}^{2}+\epsilon }}\) |
3. | Scale and shift |
| Â | \(y_{i}=\gamma \hat {x_{i}}+\beta \) |