Table 9 Stoker’s problem: hyperparameters for the TCN network
From: Deep convolutional architectures for extrapolative forecasts in time-dependent flow problems
Hyperparameters | Values |
|---|---|
Sequence length (\(n_t\)) | 5, 10, 20 |
TCN block channels | [100, 100, 100], [200, 200, 200] |
Latent dimension (m) | 25,50,125 |
Kernel size (k) | 3, 5, 7, 9 |
Activation | tanh |
Loss function | MSE |
Learning rate | \(3 \times 10^{-4}\) |
Max model parameters (\(n_t = 20\), \(m = 125\)) | 727,725 |
Min model parameters (\(n_t = 20\), \(m = 125\)) | 213,925 |