방법 비교

	심층 신뢰 신경망(Deep Belief Network, DBN)	다층 퍼셉트론 (MLP)	제한 볼츠만 머신 (Restricted Boltzmann Machine, RBM)
분야	딥러닝	딥러닝	딥러닝
계열	Machine learning	Machine learning	Latent structure
기원 연도	2006	1986	1986
창시자	Geoffrey Hinton, Simon Osindero & Yee-Whye Teh	Rumelhart, D. E.; Hinton, G. E.; Williams, R. J.	Smolensky, P. (1986); popularised by Hinton, G. E. & Salakhutdinov, R. R. (2006)
유형	Generative probabilistic model	Supervised feedforward neural network	Generative energy-based probabilistic model
원전	Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18(7), 1527–1554.	Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.	Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507.
별칭	DBN, Deep Generative Network, Stacked RBM Network, Derin İnanç Ağı	MLP, feedforward neural network, fully connected neural network, vanilla neural network	RBM, Harmonium, restricted Boltzmann machine, RBM generative model
관련	3	4	3
요약	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 Multilayer Perceptron is a classic fully connected feedforward neural network trained with the backpropagation algorithm, as formalised by Rumelhart, Hinton & Williams in their landmark 1986 Nature paper. Composed of an input layer, one or more hidden layers of neurons, and an output layer, the MLP learns nonlinear mappings from input features to target outputs and serves as the foundational building block of modern deep learning.	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.