Machine learning

Generativna suparnička mreža

Generativna suparnička mreža (GAN), koju su uveli Ian Goodfellow i saradnici 2014. godine, proizvodi realistične sintetičke podatke kroz nadmetanje dve neuralne mreže — generatora i diskriminatora. Široko se koristi za sintezu slika, uvećanje podataka i procenu distribucije.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

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

+20 more

Izvori

  1. Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link
  2. Karras, T. et al. (2020). Analyzing and Improving the Image Quality of StyleGAN. CVPR. DOI: 10.1109/CVPR42600.2020.00813

Kako citirati ovu stranicu

ScholarGate. (2026, June 1). Generative Adversarial Network (GAN). ScholarGate. https://scholargate.app/sr/deep-learning/generative-adversarial-network

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

ScholarGateGenerative Adversarial Network (Generative Adversarial Network (GAN)). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/generative-adversarial-network · Skup podataka: https://doi.org/10.5281/zenodo.20539026