Machine learning

N-BEATS

N-BEATS je arhitektura dubokog učenja za prognoziranje vremenskih nizova, koju su 2020. predstavili Oreshkin i suradnici, izgrađena od interpretiranih hrptova trenda i sezonalnosti. Bio je to prvi čisto neuronski model za prognoziranje koji je postigao performanse na razini najsuvremenijih na natjecanju M4, bez oslanjanja na bilo koje klasične statističke komponente.

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.

Izvori

  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

Kako citirati ovu stranicu

ScholarGate. (2026, June 1). N-BEATS (Neural Basis Expansion Analysis for Interpretable Time Series Forecasting). ScholarGate. https://scholargate.app/hr/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)). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/nbeats · Skup podataka: https://doi.org/10.5281/zenodo.20539026