ScholarGate
Msaidizi
Machine learningTime-series forecasting

TiDE: Kiendeshi chenye Msongamano wa Mfuatano wa Wakati

TiDE (Time-series Dense Encoder) ni usanifu wa kiendeshi-kidodishi kinachotegemea MLP kwa utabiri wa mfuatano mrefu wa wakati wenye vigeu vingi, ulioanzishwa na Abhimanyu Das na wenzake katika Google Research mwaka 2023. Kielelezo huchanganua uchunguzi wa zamani wa mfuatano wa wakati pamoja na vigeu tuli na vinavyobadilika kupitia tabaka za MLP zilizowekwa, kisha hutoa uwakilishi fiche kuwa utabiri wa siku zijazo. TiDE inaonyesha kuwa miundo rahisi ya mstari na yenye msongamano inaweza kufikia au kuzidi miundo inayotegemea Transformer kwenye vipimo vya kawaida vya utabiri wa muda mrefu huku ikiwa na kasi zaidi.

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.

TiDE: Kiendeshi chenye Msongamano wa Mfuatano wa Wakati
DLinear: Muundo Linganif…Multilayer Perceptron (M…TSMixer: Usanifu wa All-…

Vyanzo

  1. Das, A., Kong, W., Leach, A., Mathur, S., Sen, R., & Yu, R. (2023). Long-term forecasting with TiDE: Time-series dense encoder. Transactions on Machine Learning Research. link

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 2). TiDE (Time-series Dense Encoder). ScholarGate. https://scholargate.app/sw/deep-learning/tide

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
ScholarGateTiDE (TiDE (Time-series Dense Encoder)). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/tide · Seti ya data: https://doi.org/10.5281/zenodo.20539026