ScholarGate
Asistent

Porovnat metody

Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.

Informer×iTransformer: Invertovaný Transformer pro predikci vícerozměrných časových řad×
OborHluboké učeníHluboké učení
RodinaMachine learningMachine learning
Rok vzniku20212024
TvůrceZhou, H. et al.Yong Liu et al.
TypTransformer (ProbSparse self-attention)Inverted-attention sequence model
Původní zdrojZhou, H. et al. (2021). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. AAAI. DOI ↗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 ↗
Další názvyInformer — Uzun Dizi Transformer Tahmini, Informer transformer, ProbSparse attention forecasterInverted Transformer, iTransformer for Time Series, Inverted Attention Transformer, Ters Transformer
Příbuzné52
ShrnutíInformer 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.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.
ScholarGateDatová sada
  1. v1
  2. 2 Zdroje
  3. PUBLISHED
  1. v1
  2. 1 Zdroje
  3. PUBLISHED

Přejít na hledání Stáhnout prezentaci

ScholarGatePorovnat metody: Informer · iTransformer. Získáno 2026-06-17 z https://scholargate.app/cs/compare