Gradient-based learning applied to document recognition
E74104
"Gradient-based learning applied to document recognition" is a seminal 1998 paper by Yann LeCun and colleagues that introduced and demonstrated the effectiveness of convolutional neural networks for tasks like handwritten digit recognition, helping to lay the foundations of modern deep learning.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Gradient-based learning applied to document recognition canonical | 3 |
How this entity was disambiguated
This entity first appeared as the object of triple T591895 — 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: Gradient-based learning applied to document recognition Context triple: [LeNet, notablePublication, Gradient-based learning applied to document recognition]
-
A.
“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.
-
B.
“A fast learning algorithm for deep belief nets”
“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.
-
C.
Hopfield networks
Hopfield networks are recurrent artificial neural networks that serve as content-addressable memory systems, storing patterns as stable states and retrieving them through dynamics that minimize an energy function.
-
D.
Deep belief networks
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.
-
E.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
- 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: Gradient-based learning applied to document recognition Target entity description: "Gradient-based learning applied to document recognition" is a seminal 1998 paper by Yann LeCun and colleagues that introduced and demonstrated the effectiveness of convolutional neural networks for tasks like handwritten digit recognition, helping to lay the foundations of modern deep learning.
-
A.
“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.
-
B.
“A fast learning algorithm for deep belief nets”
“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.
-
C.
Hopfield networks
Hopfield networks are recurrent artificial neural networks that serve as content-addressable memory systems, storing patterns as stable states and retrieving them through dynamics that minimize an energy function.
-
D.
Deep belief networks
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.
-
E.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
- F. None of above. chosen
Statements (47)
| Predicate | Object |
|---|---|
| instanceOf |
research article
ⓘ
scientific paper ⓘ |
| affiliatedInstitution |
Bell Telephone Laboratories
ⓘ
surface form:
AT&T Bell Laboratories
Université de Montréal ⓘ |
| applicationDomain |
document recognition
ⓘ
handwritten digit recognition ⓘ |
| architectureName | LeNet ⓘ |
| author |
Léon Bottou
ⓘ
Patrick Haffner ⓘ Yann LeCun ⓘ Yoshua Bengio ⓘ |
| contribution |
demonstrated effectiveness of convolutional neural networks for document recognition
ⓘ
helped establish convolutional neural networks as a standard approach for image recognition tasks ⓘ showed that gradient-based learning can outperform hand-engineered feature systems for character recognition ⓘ |
| countryOfOrigin |
United States of America
ⓘ
surface form:
United States
|
| datasetUsed | MNIST ⓘ |
| demonstratedOn |
bank check recognition
ⓘ
handwritten ZIP code recognition ⓘ |
| field |
computer vision
ⓘ
deep learning ⓘ machine learning ⓘ pattern recognition ⓘ |
| impact |
foundational work for modern deep learning
ⓘ
widely cited in the deep learning literature ⓘ |
| influenced |
applications of deep learning to large-scale image recognition
ⓘ
development of modern convolutional neural network architectures ⓘ |
| issue | 11 ⓘ |
| language | English ⓘ |
| learningAlgorithm |
backpropagation of gradients
ⓘ
stochastic gradient descent ⓘ |
| mainConcept |
backpropagation
ⓘ
gradient-based learning ⓘ |
| mainMethod | convolutional neural networks ⓘ |
| pages | 2278–2324 ⓘ |
| problemAddressed |
automatic recognition of handwritten characters
ⓘ
robust document image understanding ⓘ |
| publicationYear | 1998 ⓘ |
| publisher | Proceedings of the IEEE ⓘ |
| shows |
hierarchical feature extraction with convolutional layers
ⓘ
superiority of learned features over handcrafted features for digit recognition ⓘ |
| technique |
end-to-end training
ⓘ
multi-layer convolutional networks ⓘ shared weights ⓘ subsampling layers ⓘ |
| timePeriod | late 1990s ⓘ |
| title | Gradient-based learning applied to document recognition self-link ⓘ |
| volume | 86 ⓘ |
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: Gradient-based learning applied to document recognition Description of subject: "Gradient-based learning applied to document recognition" is a seminal 1998 paper by Yann LeCun and colleagues that introduced and demonstrated the effectiveness of convolutional neural networks for tasks like handwritten digit recognition, helping to lay the foundations of modern deep learning.
Referenced by (3)
Full triples — surface form annotated when it differs from this entity's canonical label.
Gradient-based learning applied to document recognition
→
title
→
Gradient-based learning applied to document recognition
self-link
ⓘ