Sammenlign metoder

	Wasserstein GAN (WGAN)	Generativt motsetningsnettverk
Fagfelt	Dyp læring	Dyp læring
Familie	Machine learning	Machine learning
Opprinnelsesår	2017	2014
Opphavsperson	Martín Arjovsky, Soumith Chintala & Léon Bottou	Goodfellow, I. et al.
Type	Generative adversarial network variant	Generative deep learning (adversarial two-network game)
Opprinnelig kilde	Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. International Conference on Machine Learning (ICML), 214–223.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.
Alias	WGAN, Earth-Mover GAN, Wasserstein Generative Adversarial Network, Wasserstein-GAN	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
Relaterte	3	4
Sammendrag	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.	A 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.