ScholarGate
Asistent

Usporedite metode

Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.

Generativna suparnička mreža×Wasserstein GAN (WGAN)×
PodručjeDuboko učenjeDuboko učenje
ObiteljMachine learningMachine learning
Godina nastanka20142017
TvoracGoodfellow, I. et al.Martín Arjovsky, Soumith Chintala & Léon Bottou
VrstaGenerative deep learning (adversarial two-network game)Generative adversarial network variant
Temeljni izvorGoodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. International Conference on Machine Learning (ICML), 214–223. link ↗
Drugi naziviÜretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial networkWGAN, Earth-Mover GAN, Wasserstein Generative Adversarial Network, Wasserstein-GAN
Srodne43
SažetakA Generative Adversarial Network (GAN), introduced by Ian Goodfellow and colleagues in 2014, produces realistic synthetic data through the competition of two neural networks — a generator and a discriminator. It is widely used for image synthesis, data augmentation, and distribution estimation.Wasserstein GAN (WGAN) is a generative adversarial network variant introduced by Arjovsky, Chintala, and Bottou in 2017 that replaces the Jensen-Shannon divergence used in the original GAN with the Wasserstein-1 (Earth Mover) distance. This substitution provides a theoretically grounded training objective that yields more stable optimization and a loss value that correlates meaningfully with generated sample quality, addressing the notorious mode collapse and vanishing gradient problems of standard GANs.
ScholarGateSkup podataka
  1. v1
  2. 2 Izvori
  3. PUBLISHED
  1. v1
  2. 1 Izvori
  3. PUBLISHED

Idi na pretraživanje Preuzmi prezentaciju

ScholarGateUsporedite metode: Generative Adversarial Network · Wasserstein GAN. Preuzeto 2026-06-19 s https://scholargate.app/hr/compare