Zapis dokaza metode

Time-MoE

Time-MoE is a billion-scale autoregressive foundation model for universal time-series forecasting, introduced by Shi et al. in 2024 and accepted at ICLR 2025. It combines a decoder-only transformer architecture with sparse Mixture-of-Experts (MoE) feed-forward layers, enabling the model to scale to billions of parameters while activating only a small subset of expert networks per token—dramatically increasing capacity without proportional compute cost.

Sources recorded, not reviewed

Izvorni zapis

Citati kopirani doslovno iz izvornog zapisa metode. Ne impliciraju nikakvu provjeru na razini tvrdnje.

Time-MoE (Mixture-of-Experts Time-Series Foundation Model)

Taksonomski zapis metode · ml-model / deep-learning

Shi, X., Wang, S., Nie, Y., Li, D., Ye, Z., Wen, Q., & Jin, M. (2024). Time-MoE: Billion-scale time series foundation models with mixture of experts. ICLR 2025. · URL

Otvori cijelu metodu

Uređene tvrdnje

Tvrdnje pohranjene u knjigu dokaza, svaka s vlastitom procjenom.

Nema uređenih tvrdnji

Ovaj prikaz ne izmišlja procjenu tvrdnje kada knjiga dokaza nema nijednu.

Povezane metode

Generirano iz grafa metode i prikazano kao strojno predložene relacije — ne implicira se nikakva tvrdnja dokaza.

Taxonomic bucketChronosmachine-suggested · Relational suggestion, not evidence.Same method familyMixture of Expertsmachine-suggested · Relational suggestion, not evidence.Taxonomic bucketTimesFMmachine-suggested · Relational suggestion, not evidence.