Informer
Informer er en Transformer-baseret model introduceret af Zhou et al. i 2021 til lang-sekvens tidsserie-prognoser, der anvender en ProbSparse self-attention mekanisme, som reducerer den beregningsmæssige kompleksitet af standard Transformer til O(L log L). Den er bygget til problemer, der kræver forudsigelser over tusindvis af fremtidige trin.
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.
+3 more
Kilder
- Zhou, H. et al. (2021). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. AAAI. DOI: 10.1609/aaai.v35i12.17325 ↗
- Wu, H., Xu, J., Wang, J. & Long, M. (2021). Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting. NeurIPS 34. link ↗
Sådan citerer du denne side
ScholarGate. (2026, June 1). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. ScholarGate. https://scholargate.app/da/deep-learning/informer
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
- 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 →