Informer
Informer je model zasnovan na Transformeru, koji su uveli Zhou et al. 2021. godine za prognoziranje vremenskih serija sa dugim sekvencama, koristeći mehanizam samo-pažnje (self-attention) tipa ProbSparse koji smanjuje računarsku složenost standardnog Transformera na O(L log L). Izgrađen je za probleme koji zahtevaju predviđanja na hiljade budućih koraka.
Pročitajte celu metodu
Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.
Method map
The neighbourhood of related methods — select a node to explore.
+3 more
Izvori
- 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 ↗
Kako citirati ovu stranicu
ScholarGate. (2026, June 1). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. ScholarGate. https://scholargate.app/sr/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.
- Model ARIMA (Autoregressive Integrated Moving Average)Ekonometrija↔ compare
- DeepARDuboko učenje↔ compare
- N-HiTSDuboko učenje↔ compare
- PatchTSTDuboko učenje↔ compare
- Slučajna šumaMašinsko učenje↔ compare
Citirana u
Uočili ste grešku na ovoj stranici? Prijavite je ili predložite ispravku →