“A fast learning algorithm for deep belief nets”
E11232
“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.
All labels observed (3)
| Label | Occurrences |
|---|---|
| A fast learning algorithm for deep belief nets | 2 |
| "A Fast Learning Algorithm for Deep Belief Nets" | 1 |
| “A fast learning algorithm for deep belief nets” canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T93176 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: “A fast learning algorithm for deep belief nets” Context triple: [Geoffrey Hinton, notableWork, “A fast learning algorithm for deep belief nets”]
-
A.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
-
B.
“Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
-
C.
Deep Learning (book)
Deep Learning (book) is a foundational textbook that systematically introduces the theory and practice of modern deep neural networks, co-authored by leading researchers including Yoshua Bengio.
-
D.
Lifelong Learning Machines program
The Lifelong Learning Machines program is a DARPA research initiative aimed at developing AI systems that can continuously learn and adapt from experience in dynamic, real-world environments.
-
E.
Google Brain
Google Brain is a deep learning research team at Google that pioneered many advances in neural networks and artificial intelligence.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: “A fast learning algorithm for deep belief nets” Target entity description: “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.
-
A.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
-
B.
“Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
-
C.
Deep Learning (book)
Deep Learning (book) is a foundational textbook that systematically introduces the theory and practice of modern deep neural networks, co-authored by leading researchers including Yoshua Bengio.
-
D.
Lifelong Learning Machines program
The Lifelong Learning Machines program is a DARPA research initiative aimed at developing AI systems that can continuously learn and adapt from experience in dynamic, real-world environments.
-
E.
Google Brain
Google Brain is a deep learning research team at Google that pioneered many advances in neural networks and artificial intelligence.
- F. None of above. chosen
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
ⓘ
linked to:
Geoffrey 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
ⓘ
linked to:
Boltzmann machines
|
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: “A fast learning algorithm for deep belief nets” Description of subject: “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.
Referenced by (4)
Full triples — surface form annotated when it differs from this entity's canonical label.
linked to: “A fast learning algorithm for deep belief nets”
linked to: “A fast learning algorithm for deep belief nets”
linked to: “A fast learning algorithm for deep belief nets”