ScholarGate
Msaidizi
Machine learningTime-series forecasting

Crossformer: Transfoma ya Utegemezi wa Vipimo-Mtambuka kwa Utabiri wa Mfululizo wa Muda wa Vigezo Vingi

Crossformer ni usanifu unaotegemea Transfoma kwa utabiri wa mfululizo wa muda wa vigezo vingi, ulioanzishwa na Yunhao Zhang na Junchi Yan katika ICLR 2023. Tofauti na lahaja za awali za Transfoma zinazochukulia kila kigezo kivyake, Crossformer huiga waziwazi vitegemezi vya vipimo-mtambuka sambamba na mifumo ya muda. Inafanikisha hili kupitia muundo wa umakini wa hatua mbili — muda-mtambuka na vipimo-mtambuka — unaotumika kwenye viingilizi vya kiwango cha sehemu vilivyopangwa katika kirekodi cha kihierarkia, kuwezesha modeli kunasa mienendo ya ndani ya kigezo na uhusiano kati ya vigezo kwa wakati mmoja.

Fungua katika MethodMindHivi karibuniVideoHivi karibuniDownload slides

Soma mbinu kamili

Kwa wanachama pekee

Ingia kwa akaunti ya bure ili kusoma sehemu hii.

Ingia

Method map

The neighbourhood of related methods — select a node to explore.

Vyanzo

  1. Zhang, Y., & Yan, J. (2023). Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. ICLR. link

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 2). Crossformer (Cross-Dimension Dependency Transformer). ScholarGate. https://scholargate.app/sw/deep-learning/crossformer

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

Imerejelewa na

ScholarGateCrossformer (Crossformer (Cross-Dimension Dependency Transformer)). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/crossformer · Seti ya data: https://doi.org/10.5281/zenodo.20539026