Deep belief networks

E46988

Deep belief networks are a class of deep generative neural network models composed of stacked layers of latent variables, typically built from restricted Boltzmann machines, used for unsupervised feature learning and representation.

Jump to: Statements Referenced by

Statements (50)

Predicate Object
instanceOf artificial neural network architecture
deep generative model
probabilistic graphical model
representation learning model
unsupervised learning model
assume directed connections in upper layers
undirected connections in lower layers
basedOn restricted Boltzmann machines
canModel complex data distributions
high-dimensional data
composedOf multiple layers of latent variables
stacked restricted Boltzmann machines
describedIn “A fast learning algorithm for deep belief nets”
surface form: "A Fast Learning Algorithm for Deep Belief Nets"
developedBy Geoffrey Hinton
Simon Osindero
Yee-Whye Teh
field artificial intelligence
machine learning
hasProperty deep architecture
distributed representations
energy-based formulation
generative
hierarchical feature learning
layer-wise training
probabilistic
stochastic hidden units
unsupervised pretraining
inspired later deep learning pretraining methods
introducedIn 2006
publishedIn Neural Computation
relatedTo autoencoders
Boltzmann machines
surface form: deep Boltzmann machines

deep neural networks
energy-based models
restricted Boltzmann machines
variational autoencoders
trainedBy backpropagation fine-tuning
contrastive divergence
greedy layer-wise pretraining
stochastic gradient descent
usedFor classification
data generation
dimensionality reduction
dimensionality reduction for visualization
image recognition
pretraining deep neural networks
regression
representation learning
speech recognition
unsupervised feature learning

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.

Boltzmann machines inspired Deep belief networks