Machine learning

Informer

Informer je model utemeljen na Transformeru, predstavljen od strane Zhoua i suradnika 2021. godine za prognoziranje vremenskih nizova na dugim sekvencama, koristeći mehanizam samopozornosti ProbSparse koji smanjuje računalnu složenost standardnog Transformera na O(L log L). Izgrađen je za probleme koji zahtijevaju predviđanja na tisuće budućih koraka.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

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

+3 more

Izvori

  1. Zhou, H. et al. (2021). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. AAAI. DOI: 10.1609/aaai.v35i12.17325
  2. Wu, H., Xu, J., Wang, J. & Long, M. (2021). Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting. NeurIPS 34. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 1). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. ScholarGate. https://scholargate.app/hr/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.

Compare side by side

Citirana u

ScholarGateInformer (Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/informer · Skup podataka: https://doi.org/10.5281/zenodo.20539026