Porovnat metody

	Variační autoenkodér	Analýza hlavních komponent
Obor	Hluboké učení	Strojové učení
Rodina	Machine learning	Machine learning
Rok vzniku	2014	2002
Tvůrce	Kingma, D. P. & Welling, M.	Jolliffe, I.T. (textbook); Pearson & Hotelling (origins)
Typ	Deep generative latent-variable model (encoder–decoder)	Unsupervised dimensionality reduction
Původní zdroj	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).	Jolliffe, I.T. (2002). Principal Component Analysis (2nd ed.). Springer.
Další názvy	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model	Temel Bileşenler Analizi (PCA), PCA, principal components analysis, Karhunen-Loève transform
Příbuzné	5	3
Shrnutí	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.	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.