Table 1 Network architecture and parameters used in this work.
From: Heuristic machinery for thermodynamic studies of SU(N) fermions with neural networks
Layer | Layer name | Function | Description |
|---|---|---|---|
1 | Input | Image input | 201 × 201 Images |
2 | Conv. layer | Convolution | 24 24 × 24 Convolutions with stride (1,1) |
3 | ReLU | Activation function | ReLU function |
4 | Pool layer | Average pooling | 2 × 2 With stride (1,1) |
5 | Dropout | Dropout | 50% Dropout |
6 | Fully conn. layer | Fully connected | Fully connected layer with 4 neurons |
7 | Softmax | Activation function | Softmax function |
8 | Output | Classification output | Probability with classes N=1,2,5,6 |
