ScholarGate
Assistent
Machine learning

N-BEATS

N-BEATS er en deep learning-arkitektur til tidsserieprognoser, introduceret af Oreshkin og kolleger i 2020, bygget af fortolkelige trend- og sæsonstakke. Det var den første rent neurale prognosemodel, der opnåede state-of-the-art-performance i M4-konkurrencen uden at anvende klassiske statistiske komponenter.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

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

Kilder

  1. Oreshkin, B.N. et al. (2020). N-BEATS: Neural Basis Expansion Analysis for Interpretable Time Series Forecasting. ICLR. link
  2. Makridakis, S., Spiliotis, E. & Assimakopoulos, V. (2020). The M4 Competition: 100,000 Time Series and 61 Forecasting Methods. International Journal of Forecasting, 36(1), 54–74. DOI: 10.1016/j.ijforecast.2019.04.014

Sådan citerer du denne side

ScholarGate. (2026, June 1). N-BEATS (Neural Basis Expansion Analysis for Interpretable Time Series Forecasting). ScholarGate. https://scholargate.app/da/deep-learning/nbeats

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
ScholarGateN-BEATS (N-BEATS (Neural Basis Expansion Analysis for Interpretable Time Series Forecasting)). Hentet 2026-06-15 fra https://scholargate.app/da/deep-learning/nbeats · Datasæt: https://doi.org/10.5281/zenodo.20539026