Table 3 Model structure and training parameter configuration table.
From: Artificial intelligence CNN for information system optimization and decision support model
Parameter category | Project name | Parameter setting |
|---|---|---|
Network structure | Number of convolution layers | 3 layers |
Convolution kernel size | 5 | |
Port number | 32 → 64 → 128 | |
Activation function | ReLU | |
Pool mode | Max Pooling | |
Classified output layer | Output structure | Fully connected layer + Softmax classification |
Training parameters | Loss function | Cross entropy loss |
Optimizer | Adam | |
Initial learning rate | 0.001 | |
Batch size | 64 | |
Number of training rounds (Epochs) | 50 | |
Regularization method | Dropout (p = 0.3) + BatchNorm |
