Σύγκριση μεθόδων

	Μηχανή Boltzmann Περιορισμένης Δομής (RBM)	Variational Autoencoder
Πεδίο	Βαθιά Μάθηση	Βαθιά Μάθηση
Οικογένεια	Latent structure	Machine learning
Έτος προέλευσης	1986	2014
Δημιουργός	Smolensky, P. (1986); popularised by Hinton, G. E. & Salakhutdinov, R. R. (2006)	Kingma, D. P. & Welling, M.
Τύπος	Generative energy-based probabilistic model	Deep generative latent-variable model (encoder–decoder)
Θεμελιώδης πηγή	Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
Εναλλακτικές ονομασίες	RBM, Harmonium, restricted Boltzmann machine, RBM generative model	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
Συναφείς	3	5
Σύνοψη	A Restricted Boltzmann Machine is a two-layer generative probabilistic model consisting of visible (observed) and hidden (latent) binary units connected by an undirected bipartite graph with no within-layer connections. Originally introduced as the 'Harmonium' by Paul Smolensky in 1986 and powerfully revived by Geoffrey Hinton and Ruslan Salakhutdinov in their landmark 2006 Science paper, RBMs became historically pivotal as the building block for greedy layer-wise pre-training of Deep Belief Networks, restarting interest in deep neural networks after years of stagnation.	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.