TABLE II.
Hyperparamter | Value |
---|---|
Network architecture (channels) | [1024, 512, 512, 1] |
Activation function | [ReLu, ReLu, ReLu, Sigmoid] |
Similarity Function | Gaussian |
Maximum Epochs | 5000 |
Learning Rate | 1e-5 |
Optimizer | ADAM |
λ1 ( parameter) | 1e-4 |
λ2 (RLap parameter) | 0.005 |
Learning rate exponential decay | 0.9/1000 epochs |