Machine learning

Temporal Fusion Transformer

Temporal Fusion Transformer (TFT), koji su predstavili Lim, Arık, Loeff i Pfister 2021. godine, jeste interpretativna arhitektura dubokog učenja za prognoziranje vremenskih serija sa višestrukim horizontom. Kombinuje selekciju varijabli, gejtovanje, pažnju na višestrukom horizontu i kvantilne izlaze, obrađujući statičke, prošle i poznate buduće ulaze zajedno radi generisanja prognoza sa više koraka.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. 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
  2. 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

Kako citirati ovu stranicu

ScholarGate. (2026, June 1). Temporal Fusion Transformer for Interpretable Multi-Horizon Time Series Forecasting. ScholarGate. https://scholargate.app/sr/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.

Compare side by side

Citirana u

ScholarGateTemporal Fusion Transformer (Temporal Fusion Transformer for Interpretable Multi-Horizon Time Series Forecasting). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/temporal-fusion-transformer · Skup podataka: https://doi.org/10.5281/zenodo.20539026