Table 6 Stoker’s problem: training, validation and testing dataset
From: Deep convolutional architectures for extrapolative forecasts in time-dependent flow problems
Dataset | Samples | Input | Output |
|---|---|---|---|
Training | 1 | \([z^{1},..., z^{n_t-1}, z^{n_t}]\) | \(z^{n_t+1}\) |
2 | \([z^{2},..., z^{n_t}, z^{n_t+1}]\) | \(z^{n_t+2}\) | |
... | ... | ... | |
250 | \([z^{250},..., z^{n_t+248}, z^{n_t+249}]\) | \(z^{n_t+250}\) (training end) | |
Validation | 251 | \([z^{251},..., z^{n_t+249}, z^{n_t+250}]\) | \(z^{n_t+251}\) |
... | ... | ... | |
260 | \([z^{260},..., z^{n_t+258}, z^{n_t + 259}]\) | \(z^{n_t+260}\) | |
Testing | 1 | \([z^{1},..., z^{n_t-1}, z^{n_t}]\) | \([z^{n_t+1},..., z^{449}, z^{450}]\) |