Сравнение методов

	Автоэнкодер	Анализ главных компонент	Вариационный автокодировщик
Область	Глубокое обучение	Машинное обучение	Глубокое обучение
Семейство	Machine learning	Machine learning	Machine learning
Год появления	2006	2002	2014
Автор метода	Hinton, G.E. & Salakhutdinov, R.R.	Jolliffe, I.T. (textbook); Pearson & Hotelling (origins)	Kingma, D. P. & Welling, M.
Тип	Neural network (encoder-decoder)	Unsupervised dimensionality reduction	Deep generative latent-variable model (encoder–decoder)
Основополагающий источник	Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507.	Jolliffe, I.T. (2002). Principal Component Analysis (2nd ed.). Springer.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
Другие названия	Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network	Temel Bileşenler Analizi (PCA), PCA, principal components analysis, Karhunen-Loève transform	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
Связанные	4	3	5
Сводка	An autoencoder is an encoder-decoder neural network, popularised by Hinton and Salakhutdinov in 2006, that compresses data into a low-dimensional latent code and then reconstructs it, enabling dimensionality reduction and anomaly detection. By learning to rebuild its own input through a narrow bottleneck, it discovers a compact representation of the data.	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.	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.