방법 비교

	준지도 학습 GAN	Variational Autoencoder
분야	딥러닝	딥러닝
계열	Machine learning	Machine learning
기원 연도	2016	2014
창시자	Odena, A.; Salimans, T. et al.	Kingma, D. P. & Welling, M.
유형	Semi-supervised generative model	Deep generative latent-variable model (encoder–decoder)
원전	Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved Techniques for Training GANs. Advances in Neural Information Processing Systems (NeurIPS), 29.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
별칭	SGAN, Semi-GAN, semi-supervised generative adversarial network, GAN-based semi-supervised learning	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
관련	5	5
요약	Semi-supervised GAN (SGAN) extends the standard GAN discriminator to simultaneously classify labeled examples into K real classes and detect generated fakes as a (K+1)-th class, letting the generator's synthetic data act as implicit regularization and allowing strong classifiers to be trained with very few labeled examples.	The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning.