ScholarGate
Msaidizi
Machine learningTime-series forecasting

Moirai: Kituo cha Utabiri wa Wakati-Mfululizo wa Ulimwengu

Moirai ni mfumo msingi wa utabiri wa wakati-mfululizo wa ulimwengu ulioanzishwa na Gerald Woo na wenzake katika Utafiti wa Salesforce mnamo 2024 na kuwasilishwa katika ICML. Wazo kuu ni kuandaa awali Transformer kubwa moja kwenye mkusanyiko wa kipekee wa data ya mfululizo wa wakati (LOTSA) unaojumuisha nyanja na masafa mengi, kuwezesha utabiri wa sifuri-risasi na wachache-risasi kwenye seti za data ambazo hazijaonekana bila mafunzo upya maalum kwa kazi. Moirai hutumia tokenization inayotokana na kiraka, hisia za aina yoyote, na kichwa cha pato cha mchanganyiko wa usambazaji ili kushughulikia masafa tofauti, aina mbalimbali, na utabiri wa uwezekano katika usanifu umoja.

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. Woo, G., Liu, C., Kumar, A., Xiong, C., Savarese, S., & Sahoo, D. (2024). Unified training of universal time series forecasting transformers. ICML. link

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 2). Moirai (Universal Time-Series Forecasting Transformer). ScholarGate. https://scholargate.app/sw/deep-learning/moirai

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

ScholarGateMoirai (Moirai (Universal Time-Series Forecasting Transformer)). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/moirai · Seti ya data: https://doi.org/10.5281/zenodo.20539026