Võrdle meetodeid
Vaata valitud meetodeid kõrvuti; erinevad read on esile tõstetud.
| Informer× | N-HiTS× | PatchTST× | |
|---|---|---|---|
| Valdkond | Süvaõpe | Süvaõpe | Süvaõpe |
| Perekond | Machine learning | Machine learning | Machine learning |
| Tekkeaasta≠ | 2021 | 2023 | 2023 |
| Looja≠ | Zhou, H. et al. | Challu, C. et al. | Nie, Y. et al. |
| Tüüp≠ | Transformer (ProbSparse self-attention) | Deep neural forecasting (hierarchical interpolation) | Transformer for time series forecasting |
| Algallikas≠ | Zhou, H. et al. (2021). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. AAAI. DOI ↗ | Challu, C. et al. (2023). NHITS: Neural Hierarchical Interpolation for Time Series Forecasting. AAAI. 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 ↗ |
| Rööpnimetused | Informer — Uzun Dizi Transformer Tahmini, Informer transformer, ProbSparse attention forecaster | N-HiTS — Hiyerarşik İnterpolasyon Tahmini, NHITS, Neural Hierarchical Interpolation | PatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer |
| Seotud≠ | 5 | 3 | 3 |
| Kokkuvõte≠ | Informer is a Transformer-based model introduced by Zhou et al. in 2021 for long-sequence time-series forecasting, using a ProbSparse self-attention mechanism that lowers the computational complexity of the standard Transformer to O(L log L). It is built for problems that demand predictions across thousands of future steps. | N-HiTS (Neural Hierarchical Interpolation for Time Series Forecasting), introduced by Challu and colleagues in 2023, is a deep neural forecasting architecture that combines the hierarchical forecasts of multiple stacks operating at different sampling rates and merges them through interpolation. It extends N-BEATS to deliver markedly better accuracy on long forecast horizons. | 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. |
| ScholarGateAndmestik ↗ |
|
|
|