Jämför metoder
Granska de valda metoderna sida vid sida; rader som skiljer sig är markerade.
| iTransformer: Inverterad Transformer för multivariat tidsserieprognostisering× | PatchTST× | |
|---|---|---|
| Ämnesområde | Djupinlärning | Djupinlärning |
| Familj | Machine learning | Machine learning |
| Ursprungsår≠ | 2024 | 2023 |
| Upphovsperson≠ | Yong Liu et al. | Nie, Y. et al. |
| Typ≠ | Inverted-attention sequence model | Transformer for time series forecasting |
| Ursprungskälla≠ | Liu, Y., Hu, T., Zhang, H., Wu, H., Wang, S., Ma, L., & Long, M. (2024). iTransformer: Inverted transformers are effective for time series forecasting. ICLR. link ↗ | Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR. link ↗ |
| Alias≠ | Inverted Transformer, iTransformer for Time Series, Inverted Attention Transformer, Ters Transformer | PatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer |
| Närliggande≠ | 2 | 3 |
| Sammanfattning≠ | iTransformer is a deep-learning architecture for multivariate time-series forecasting introduced by Liu et al. at ICLR 2024. Its defining idea is to invert the conventional Transformer tokenisation strategy: instead of treating each time step as a token, iTransformer treats each variate (sensor channel or feature series) as a single token whose embedding encodes the full observed look-back window. Self-attention is then applied across variates to capture inter-series dependencies, while a feed-forward network within each token learns temporal patterns. | 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. |
| ScholarGateDatamängd ↗ |
|
|