ScholarGate
Msaidizi
Machine learningTime-series forecasting

TimesFM: Muundo wa Msingi wa Msomaji Pekee kwa Utambuzi wa Utendaji wa Wakati

TimesFM ni muundo wa msingi uliopatiwa mafunzo awali kwa ajili ya utabiri wa utendaji wa wakati mmoja ulioanzishwa na Abhimanyu Das, Weihao Kong, Rajat Sen, na Yichen Zhou kutoka Google mwaka 2024. Muundo huu unatumia usanifu wa transformer wa msomaji pekee, unaofanana na akili bandia za lugha, na umefunzwa kwa kiasi kikubwa cha data halisi na bandia ya utendaji wa wakati. Ubunifu wake mkuu ni uwezo wa kufanya utabiri sahihi wa sifuri-risasi katika nyanja mbalimbali bila kuhitaji marekebisho maalum kwa ajili ya kazi.

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. Das, A., Kong, W., Sen, R., & Zhou, Y. (2024). A decoder-only foundation model for time-series forecasting. ICML. link

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 2). TimesFM (Time-series Foundation Model). ScholarGate. https://scholargate.app/sw/deep-learning/timesfm

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

ScholarGateTimesFM (TimesFM (Time-series Foundation Model)). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/timesfm · Seti ya data: https://doi.org/10.5281/zenodo.20539026