ScholarGate
Msaidizi
Machine learningTime-series forecasting

Non-stationary Transformer

Non-stationary Transformer ni usanifu wa kutabiri mfululizo wa nyakati kulingana na Transformer ulioanzishwa na Yong Liu, Haixu Wu, Jianmin Wang, na Mingsheng Long katika NeurIPS 2022. Unashughulikia mvutano wa kimsingi katika kutumia Transformers kwa mfululizo wa nyakati halisi: utaratibu wa kupita kiasi wa utulivu wakati wa maandalizi ya awali huondoa ishara zisizo tulivu zinazobeba taarifa za utabiri, huku pembejeo mbichi zisizo tulivu zikisababisha umakini kuporomoka. Kifaa hiki kinatatua hili kupitia utulivu wa mfululizo pamoja na utaratibu mpya wa umakini usio tulivu unaorejesha usambazaji halisi wa muda katika utabiri.

Fungua katika MethodMindHivi karibuniVideoHivi karibuniPakua slaidi

Soma mbinu kamili

Kwa wanachama pekee

Ingia kwa akaunti ya bure ili kusoma sehemu hii.

Ingia

Ramani ya mbinu

Jirani ya mbinu zinazohusiana — chagua nodi ili kuchunguza.

Vyanzo

  1. Liu, Y., Wu, H., Wang, J., & Long, M. (2022). Non-stationary transformers: Exploring the stationarity in time series forecasting. NeurIPS. link

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 2). Non-stationary Transformers for Forecasting. ScholarGate. https://scholargate.app/sw/deep-learning/nonstationary-transformer

Mbinu ipi?

Weka mbinu hii kando ya jamaa zake wa karibu na uzisome bega kwa bega — maktaba huweka vitabu mezani; uamuzi ni wako.

Linganisha bega kwa bega

Imerejelewa na

ScholarGateNon-stationary Transformer (Non-stationary Transformers for Forecasting). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/nonstationary-transformer · Seti ya data: https://doi.org/10.5281/zenodo.20539026