ScholarGate
Assistent
Machine learning

Skooripõhine generatiivne mudel

Skooripõhine generatiivne mudel, mille tutvustasid Yang Song ja Stefano Ermon 2019. aastal ning mis üldistati stohhastilise diferentsiaalvõrrandi (SDE) raamistikuks 2021. aastal, õpib andmetiheduse gradiendi – skoori – selle asemel, et ennustada otse müra, ja kasutab seda uute näidiste genereerimiseks. See on matemaatiline üldistus, mis ühendab difusioonimudelid pideva aja formuleeringu alla.

Ava rakenduses MethodMindPeagiVideoPeagiDownload slides

Loe meetodi täielikku kirjeldust

Ainult liikmetele

Selle osa lugemiseks logi sisse tasuta kontoga.

Logi sisse

Method map

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

Allikad

  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

Kuidas sellele lehele viidata

ScholarGate. (2026, June 1). Score-Based Generative Modeling through Stochastic Differential Equations. ScholarGate. https://scholargate.app/et/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

Sellele viitavad

ScholarGateScore-Based Generative Model (Score-Based Generative Modeling through Stochastic Differential Equations). Loetud 2026-06-15 aadressilt https://scholargate.app/et/deep-learning/score-based-diffusion · Andmestik: https://doi.org/10.5281/zenodo.20539026