Research Article
An Adaptive Genetic Algorithm Optimizes Double-Hidden Layer BPNN for Rapid Detection of Moisture Content of Green Tea in Processing
Table 2
Hyperparameter setting for single-hidden layer and double-hidden layer BPNN.
| | Parameter type | 1d-BPNN | 2d-BPNN |
| | Learning rate | 0.1 | 0.01 | | Number of input nodes | 256 or 15 or 42 | 256 or 15 or 42 | | Number of hidden layers | 1 | 2 | | Number of nodes in hidden layer 1 | 15 | 32 | | Number of nodes in hidden layer 2 | None | 8 | | Number of output nodes | 1 | 1 | | Activation function | Sigmoid | Sigmoid | | Optimizer | Adam | Adam | | Momentum | 0.937 | 0.937 | | Epoch | 7000 | 10000 |
|
|
