השוואת שיטות

	רשת אמונה עמוקה (DBN)	מכונת בולצמן מוגבלת (RBM)
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Latent structure
שנת המקור	2006	1986
הוגה השיטה	Geoffrey Hinton, Simon Osindero & Yee-Whye Teh	Smolensky, P. (1986); popularised by Hinton, G. E. & Salakhutdinov, R. R. (2006)
סוג	Generative probabilistic model	Generative energy-based probabilistic model
מקור מכונן	Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527–1554.	Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507.
כינויים	DBN, Deep Generative Network, Stacked RBM Network, Derin İnanç Ağı	RBM, Harmonium, restricted Boltzmann machine, RBM generative model
קשורות	3	3
תקציר	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.	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.