Methoden vergleichen
Prüfen Sie die ausgewählten Methoden nebeneinander; abweichende Zeilen sind hervorgehoben.
| SegRNN: Segment Recurrent Neural Network für langfristige Zeitreihenprognosen× | LSTM× | PatchTST× | |
|---|---|---|---|
| Fachgebiet | Deep Learning | Deep Learning | Deep Learning |
| Familie | Machine learning | Machine learning | Machine learning |
| Entstehungsjahr≠ | 2023 | 1997 | 2023 |
| Urheber≠ | Shengsheng Lin et al. | Hochreiter, S. & Schmidhuber, J. | Nie, Y. et al. |
| Typ≠ | Segment-based recurrent forecasting model | Recurrent neural network (gated memory cell) | Transformer for time series forecasting |
| Wegweisende Quelle≠ | Lin, S., Lin, W., Wu, W., Zhao, F., Mo, R., & Zhang, H. (2023). SegRNN: Segment recurrent neural network for long-term time series forecasting. arXiv preprint. link ↗ | Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. DOI ↗ | Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR. link ↗ |
| Aliasnamen≠ | Segment RNN, Segment Recurrent Neural Network, SegRNN forecaster, Bölümlü Tekrarlayan Sinir Ağı | LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells | PatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer |
| Verwandt≠ | 3 | 5 | 3 |
| Zusammenfassung≠ | SegRNN is a recurrent neural network architecture for long-term time series forecasting proposed by Shengsheng Lin et al. in 2023. Instead of processing one time step at a time, SegRNN partitions input sequences into fixed-length segments and feeds each segment as a single token into a GRU. This segment-based design drastically reduces the number of recurrent iterations, addressing the well-known difficulty RNNs face when modeling very long dependencies over many individual steps. | LSTM (Long Short-Term Memory) is a recurrent neural network architecture, introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, that can learn long-term dependencies in sequential data and is widely used for time-series and sequence prediction. It keeps an internal memory that lets information persist across many time steps. | PatchTST is a patch-based Transformer architecture for time series forecasting, introduced by Nie and colleagues in 2023, that cuts each series into overlapping patches treated as tokens and processes channels independently. It balances computational efficiency with strong accuracy on long-horizon forecasting. |
| ScholarGateDatensatz ↗ |
|
|
|