Temporal Fusion Transformer
Temporal Fusion Transformer (TFT), introduceret af Lim, Arık, Loeff og Pfister i 2021, er en fortolkbar deep learning-arkitektur til multi-horisont tidsserieprognoser. Den kombinerer variabelselektion, gating, multi-horisont opmærksomhed og kvantiloutput, der behandler statiske, tidligere og kendte fremtidige input sammen for at producere flertrins-prognoser.
Læs hele metoden
Log ind med en gratis konto for at læse dette afsnit.
Method map
The neighbourhood of related methods — select a node to explore.
Kilder
- Lim, B., Arık, S. Ö., Loeff, N. & Pfister, T. (2021). Temporal Fusion Transformers for Interpretable Multi-Horizon Time Series Forecasting. International Journal of Forecasting, 37(4), 1748–1764. DOI: 10.1016/j.ijforecast.2021.03.012 ↗
- Lim, B. & Zohren, S. (2021). Time-Series Forecasting with Deep Learning: A Survey. Philosophical Transactions of the Royal Society A, 379(2194), 20200209. DOI: 10.1098/rsta.2020.0209 ↗
Sådan citerer du denne side
ScholarGate. (2026, June 1). Temporal Fusion Transformer for Interpretable Multi-Horizon Time Series Forecasting. ScholarGate. https://scholargate.app/da/deep-learning/temporal-fusion-transformer
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- ARIMA (Autoregressive Integrated Moving Average) ModelØkonometri↔ compare
- DeepARDyb læring↔ compare
- InformerDyb læring↔ compare
- N-HiTSDyb læring↔ compare
- PatchTSTDyb læring↔ compare
- Random ForestMaskinlæring↔ compare
Refereret af
Har du fundet en fejl på denne side? Indberet den eller foreslå en rettelse →