ScholarGate
Asistent
Machine learning

Generativni model utemeljen na ocjeni (Score-Based Generative Model)

Generativni model utemeljen na ocjeni, koji su predstavili Yang Song i Stefano Ermon 2019. godine, a 2021. generaliziran u okviru stohastičkih diferencijalnih jednadžbi (SDE), uči gradijent gustoće podataka – ocjenu – umjesto izravnog predviđanja šuma, te ga koristi za generiranje novih uzoraka. To je matematička generalizacija koja objedinjuje difuzijske modele u formulaciji kontinuiranog vremena.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. Song, Y. & Ermon, S. (2019). Generative Modeling by Estimating Gradients of the Data Distribution. NeurIPS 32, 11895–11907. link
  2. Song, Y. et al. (2021). Score-Based Generative Modeling through Stochastic Differential Equations. ICLR. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 1). Score-Based Generative Modeling through Stochastic Differential Equations. ScholarGate. https://scholargate.app/hr/deep-learning/score-based-diffusion

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

Citirana u

ScholarGateScore-Based Generative Model (Score-Based Generative Modeling through Stochastic Differential Equations). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/score-based-diffusion · Skup podataka: https://doi.org/10.5281/zenodo.20539026