iTransformer: Transformer Iliyoingizwa kwa Utabiri wa Milipuko Mingi ya Wakati
iTransformer ni usanifu wa kina wa kujifunza kwa utabiri wa milipuko mingi ya wakati ulioanzishwa na Liu et al. katika ICLR 2024. Wazo lake la kutofautisha ni kubadilisha mkakati wa kawaida wa utoaji wa ishara wa Transformer: badala ya kutibu kila hatua ya wakati kama ishara, iTransformer hutibu kila anuwai (kituo cha sensor au mfululizo wa huduma) kama ishara moja ambayo uwekaji wake wa ndani unarekodi dirisha zima la kuangalia lililoonekana. Kujitahidi kwa umakini hutumiwa kote kwa anuwai kukamata utegemezi kati ya mfululizo, wakati mtandao wa mbele wa kulisha ndani ya kila ishara hujifunza ruwaza za muda.
Soma mbinu kamili
Ingia kwa akaunti ya bure ili kusoma sehemu hii.
Method map
The neighbourhood of related methods — select a node to explore.
Vyanzo
- Liu, Y., Hu, T., Zhang, H., Wu, H., Wang, S., Ma, L., & Long, M. (2024). iTransformer: Inverted transformers are effective for time series forecasting. ICLR. link ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 2). iTransformer (Inverted Transformer for Forecasting). ScholarGate. https://scholargate.app/sw/deep-learning/itransformer
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.
- CrossformerUjifunzaji wa Kina↔ compare
- PatchTSTUjifunzaji wa Kina↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →