השוואת שיטות

	מפענח אוטומטי וריאציוני	מפענח-מצפין (Autoencoder)	רשת יריבות יוצרת (Generative Adversarial Network)	ניתוח רכיבים עיקריים
תחום	למידה עמוקה	למידה עמוקה	למידה עמוקה	למידת מכונה
משפחה	Machine learning	Machine learning	Machine learning	Machine learning
שנת המקור	2014	2006	2014	2002
הוגה השיטה	Kingma, D. P. & Welling, M.	Hinton, G.E. & Salakhutdinov, R.R.	Goodfellow, I. et al.	Jolliffe, I.T. (textbook); Pearson & Hotelling (origins)
סוג	Deep generative latent-variable model (encoder–decoder)	Neural network (encoder-decoder)	Generative deep learning (adversarial two-network game)	Unsupervised dimensionality reduction
מקור מכונן	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).	Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507.	Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS.	Jolliffe, I.T. (2002). Principal Component Analysis (2nd ed.). Springer.
כינויים	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model	Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network	Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network	Temel Bileşenler Analizi (PCA), PCA, principal components analysis, Karhunen-Loève transform
קשורות	5	4	4	3
תקציר	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.	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.	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.