方法对比

	受限玻尔tzmann机 (RBM)	深度信念网络 (DBN)	变分自编码器
领域	深度学习	深度学习	深度学习
方法族	Latent structure	Machine learning	Machine learning
起源年份	1986	2006	2014
提出者	Smolensky, P. (1986); popularised by Hinton, G. E. & Salakhutdinov, R. R. (2006)	Geoffrey Hinton, Simon Osindero & Yee-Whye Teh	Kingma, D. P. & Welling, M.
类型	Generative energy-based probabilistic model	Generative probabilistic model	Deep generative latent-variable model (encoder–decoder)
开创性文献	Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507.	Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527–1554.	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).
别名	RBM, Harmonium, restricted Boltzmann machine, RBM generative model	DBN, Deep Generative Network, Stacked RBM Network, Derin İnanç Ağı	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model
相关	3	3	5
摘要	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.	A Deep Belief Network is a generative probabilistic model composed of multiple layers of stochastic, latent variables. Introduced by Hinton, Osindero, and Teh in 2006, DBNs were among the first deep architectures to be trained efficiently. Each pair of adjacent layers forms a Restricted Boltzmann Machine, and the network is trained greedily, one layer at a time, before optional supervised fine-tuning. DBNs revived interest in deep learning and demonstrated that hierarchical feature learning from raw data is tractable.	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.