ScholarGate
Assistent
Machine learning

N-HiTS

N-HiTS (Neural Hierarchical Interpolation for Time Series Forecasting), introduceret af Challu og kolleger i 2023, er en dyb neural prognosearkitektur, der kombinerer hierarkiske prognoser fra flere stakke, der opererer ved forskellige samplingsrater, og fletter dem sammen gennem interpolation. Den udvider N-BEATS til at levere markant bedre nøjagtighed på lange prognosehorisonter.

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. Challu, C. et al. (2023). NHITS: Neural Hierarchical Interpolation for Time Series Forecasting. AAAI. DOI: 10.1609/aaai.v37i6.25854
  2. Oreshkin, B.N. et al. (2020). N-BEATS: Neural Basis Expansion Analysis for Interpretable Time Series Forecasting. ICLR. arXiv: 1905.10437 link

Sådan citerer du denne side

ScholarGate. (2026, June 1). Neural Hierarchical Interpolation for Time Series Forecasting. ScholarGate. https://scholargate.app/da/deep-learning/nhits

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

Refereret af

ScholarGateN-HiTS (Neural Hierarchical Interpolation for Time Series Forecasting). Hentet 2026-06-15 fra https://scholargate.app/da/deep-learning/nhits · Datasæt: https://doi.org/10.5281/zenodo.20539026