Σύγκριση μεθόδων

	Temporal Fusion Transformer	Ενημερωτής
Πεδίο	Βαθιά Μάθηση	Βαθιά Μάθηση
Οικογένεια	Machine learning	Machine learning
Έτος προέλευσης	2021	2021
Δημιουργός	Lim, B., Arık, S. Ö., Loeff, N. & Pfister, T.	Zhou, H. et al.
Τύπος	Attention-based deep learning forecasting architecture	Transformer (ProbSparse self-attention)
Θεμελιώδης πηγή	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.	Zhou, H. et al. (2021). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. AAAI.
Εναλλακτικές ονομασίες	Temporal Fusion Transformer (TFT), TFT, interpretable multi-horizon forecasting transformer	Informer — Uzun Dizi Transformer Tahmini, Informer transformer, ProbSparse attention forecaster
Συναφείς	6	5
Σύνοψη	The Temporal Fusion Transformer (TFT), introduced by Lim, Arık, Loeff and Pfister in 2021, is an interpretable deep learning architecture for multi-horizon time series forecasting. It combines variable selection, gating, multi-horizon attention and quantile outputs, processing static, past and known-future inputs together to produce multi-step forecasts.	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.