Table 2 The parameters of the 3D CNN
From: Automatic seizure detection using three-dimensional CNN based on multi-channel EEG
Layer | Hidden Layer | Related parameters (kernel, kernel size, stride, dropout) | ||
|---|---|---|---|---|
1 | Conv3D + LeakyReLU | 64 | 3*3*3 | 1*1*1 |
2 | Max Pooling | Â | 2*2*2 | 2*2*2 |
3 | Conv3D + LeakyReLU | 128 | 3*3*3 | 1*1*1 |
4 | Max Pooling | Â | 2*2*2 | 1*2*2 |
5 | Conv3D + LeakyReLU | 256 | 3*3*3 | 1*1*1 |
6 | Conv3D + LeakyReLU | 256 | 3*3*3 | 1*1*1 |
7 | Max Pooling | Â | 2*2*2 | 1*2*2 |
8 | Fully connected | 4096 | ||
9 | Fully connected | 2048 | ||
Softmax | ||||