PatchTST
PatchTST ni usanifu wa Transformer unaotegemea kiraka kwa utabiri wa mfululizo wa nyakati, ulioanzishwa na Nie na wenzake mwaka 2023, ambao hukata kila mfululizo kuwa viraka vinavyoingiliana vinavyotibiwa kama alama na kuchakata chaneli kwa kujitegemea. Unalinganisha ufanisi wa kompyuta na usahihi dhabiti katika utabiri wa muda mrefu.
Soma mbinu kamili
Ingia kwa akaunti ya bure ili kusoma sehemu hii.
Method map
The neighbourhood of related methods — select a node to explore.
+4 more
Vyanzo
- Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR. link ↗
- Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L. & Jin, R. (2022). FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting. ICML. link ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 1). Patch Time Series Transformer. ScholarGate. https://scholargate.app/sw/deep-learning/patchtst
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.
- Mfumo wa ARIMA (Autoregressive Integrated Moving Average)Ekonometriki↔ compare
- Utabiri Konformali kwa Utabiri wa Mfululizo wa WakatiEkonometriki↔ compare
- Msitu NasibuUjifunzaji wa Mashine↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →