手法を比較

	ディープ・ビリーフ・ネットワーク（DBN）	多層パーセプトロン (MLP)
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2006	1986
提唱者	Geoffrey Hinton, Simon Osindero & Yee-Whye Teh	Rumelhart, D. E.; Hinton, G. E.; Williams, R. J.
種類	Generative probabilistic model	Supervised feedforward neural network
原典	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.
別名	DBN, Deep Generative Network, Stacked RBM Network, Derin İnanç Ağı	MLP, feedforward neural network, fully connected neural network, vanilla neural network
関連	3	4
概要	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.