Table 3 Theoretical computational efficiency.
Model | Transformer | Informer | LSTM |
|---|---|---|---|
Training time complexity | \(O({N^2})\) | \(O(N\log N)\) | \(O(N)\) |
Space occupancy rate | \(O({N^2})\) | \(O(N\log N)\) | \(O(N)\) |
Predict time complexity | \(O(N)\) | \(O(1)\) | \(O(N)\) |
Model | Transformer | Informer | LSTM |
|---|---|---|---|
Training time complexity | \(O({N^2})\) | \(O(N\log N)\) | \(O(N)\) |
Space occupancy rate | \(O({N^2})\) | \(O(N\log N)\) | \(O(N)\) |
Predict time complexity | \(O(N)\) | \(O(1)\) | \(O(N)\) |
