“A fast learning algorithm for deep belief nets”

E11232

deep learning paper machine learning paper scientific paper

“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.

Aliases (2)

Statements (44)

Predicate	Object
instanceOf	deep learning paper → machine learning paper → scientific paper →
architectureProperty	lower layers form a directed belief network → multiple layers of latent variables → top two layers form an undirected graphical model →
author	Geoffrey E. Hinton → Simon Osindero → Yee-Whye Teh →
citationStatus	highly cited →
contribution	demonstrated effective layer-wise unsupervised pretraining → made deep neural networks easier to train → showed that greedy learning of one layer at a time works well →
evaluationDataset	MNIST →
evaluationDomain	handwritten digit recognition →
field	artificial intelligence → deep learning → machine learning →
fineTuningMethod	backpropagation →
hasPage	https://www.cs.toronto.edu/~hinton/absps/fastnc.pdf →
impact	influenced development of modern deep learning methods → revived interest in deep neural networks →
introducesConcept	deep belief network → greedy layer-wise pretraining → unsupervised pretraining for deep networks →
language	English →
learningType	probabilistic generative learning →
networkType	deep belief network → 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 → deep neural network training → 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 → unsupervised feature learning →
trainingParadigm	generative modeling → unsupervised learning →
usesModel	restricted Boltzmann machine →

Referenced by (4)

Subject (surface form when different)	Predicate
Simon Osindero ("A fast learning algorithm for deep belief nets") →	coAuthorOf
Deep belief networks (""A Fast Learning Algorithm for Deep Belief Nets"") →	describedIn
Simon Osindero ("A fast learning algorithm for deep belief nets") →	hasPublication
Geoffrey Hinton →	notableWork