Comparer des méthodes

	Autoencodeur Variationnel	Réseau antagoniste génératif	Analyse en composantes principales
Domaine	Apprentissage profond	Apprentissage profond	Apprentissage automatique
Famille	Machine learning	Machine learning	Machine learning
Année d'origine	2014	2014	2002
Auteur d'origine	Kingma, D. P. & Welling, M.	Goodfellow, I. et al.	Jolliffe, I.T. (textbook); Pearson & Hotelling (origins)
Type	Deep generative latent-variable model (encoder–decoder)	Generative deep learning (adversarial two-network game)	Unsupervised dimensionality reduction
Source fondatrice	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.	Jolliffe, I.T. (2002). Principal Component Analysis (2nd ed.). Springer.
Alias	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network	Temel Bileşenler Analizi (PCA), PCA, principal components analysis, Karhunen-Loève transform
Apparentées	5	4	3
Résumé	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.	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.	Principal Component Analysis (PCA) is an unsupervised dimensionality-reduction method — given its modern textbook treatment by Ian Jolliffe (2002) — that compresses high-dimensional data into fewer dimensions while preserving the maximum possible variance. It re-expresses correlated variables as a small set of uncorrelated principal components ordered by how much of the data's variation each one captures.