Disambiguation evidence for “A fast learning algorithm for deep belief nets” via surface form

"A fast learning algorithm for deep belief nets"


As subject (44)

Triples where this entity appears as subject under the label "A fast learning algorithm for deep belief nets".

Predicate Object
architectureProperty lower layers form a directed belief network
architectureProperty multiple layers of latent variables
architectureProperty top two layers form an undirected graphical model
author Geoffrey Hinton
surface form: Geoffrey E. Hinton
author Simon Osindero
author Yee-Whye Teh
citationStatus highly cited
contribution demonstrated effective layer-wise unsupervised pretraining
contribution made deep neural networks easier to train
contribution showed that greedy learning of one layer at a time works well
evaluationDataset MNIST
evaluationDomain handwritten digit recognition
field artificial intelligence
field deep learning
field machine learning
fineTuningMethod backpropagation
hasPage https://www.cs.toronto.edu/~hinton/absps/fastnc.pdf
impact influenced development of modern deep learning methods
impact revived interest in deep neural networks
instanceOf deep learning paper
instanceOf machine learning paper
instanceOf scientific paper
introducesConcept deep belief network
introducesConcept greedy layer-wise pretraining
introducesConcept unsupervised pretraining for deep networks
language English
learningType probabilistic generative learning
networkType deep belief network
networkType deep generative model
optimizationMethod contrastive divergence
pretrainingRole initializes weights for subsequent supervised fine-tuning
proposesMethod stacking restricted Boltzmann machines
publicationYear 2006
publishedIn Neural Computation
relatedTo Boltzmann machines
relatedTo deep neural network training
relatedTo energy-based models
shows deep belief nets can achieve low error rates on MNIST
title A fast learning algorithm for deep belief nets
topic representation learning
topic unsupervised feature learning
trainingParadigm generative modeling
trainingParadigm unsupervised learning
usesModel Boltzmann machines
surface form: restricted Boltzmann machine

As object (2)

Triples where some other subject referred to this entity as "A fast learning algorithm for deep belief nets".

Simon Osindero coAuthorOf
"A fast learning algorithm for deep belief nets"
Simon Osindero hasPublication
"A fast learning algorithm for deep belief nets"