方法对比

	深度信念网络 (DBN)	自编码器	多层感知机 (MLP)
领域	深度学习	深度学习	深度学习
方法族	Machine learning	Machine learning	Machine learning
起源年份	2006	2006	1986
提出者	Geoffrey Hinton, Simon Osindero & Yee-Whye Teh	Hinton, G.E. & Salakhutdinov, R.R.	Rumelhart, D. E.; Hinton, G. E.; Williams, R. J.
类型	Generative probabilistic model	Neural network (encoder-decoder)	Supervised feedforward neural network
开创性文献	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.	Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536.
别名	DBN, Deep Generative Network, Stacked RBM Network, Derin İnanç Ağı	Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network	MLP, feedforward neural network, fully connected neural network, vanilla neural network
相关	3	4	4
摘要	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.	An autoencoder is an encoder-decoder neural network, popularised by Hinton and Salakhutdinov in 2006, that compresses data into a low-dimensional latent code and then reconstructs it, enabling dimensionality reduction and anomaly detection. By learning to rebuild its own input through a narrow bottleneck, it discovers a compact representation of the data.	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.