LeNet
E17289
LeNet is one of the earliest convolutional neural network architectures, pioneering modern deep learning approaches to image recognition and handwritten digit classification.
All labels observed (2)
| Label | Occurrences |
|---|---|
| LeNet canonical | 4 |
| LeNet-5 convolutional neural network (with Yann LeCun and others) | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T143842 — 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: LeNet Context triple: [Yann LeCun, knownFor, LeNet]
-
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.
Google Brain
Google Brain is a deep learning research team at Google that pioneered many advances in neural networks and artificial intelligence.
-
C.
“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.
-
D.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
-
E.
Yann LeCun
Yann LeCun is a pioneering computer scientist best known for his foundational work in deep learning and convolutional neural networks, which has profoundly shaped modern 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: LeNet Target entity description: LeNet is one of the earliest convolutional neural network architectures, pioneering modern deep learning approaches to image recognition and handwritten digit classification.
-
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.
Google Brain
Google Brain is a deep learning research team at Google that pioneered many advances in neural networks and artificial intelligence.
-
C.
“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.
-
D.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
-
E.
Yann LeCun
Yann LeCun is a pioneering computer scientist best known for his foundational work in deep learning and convolutional neural networks, which has profoundly shaped modern artificial intelligence.
- F. None of above. chosen
Statements (46)
| Predicate | Object |
|---|---|
| instanceOf |
convolutional neural network architecture
ⓘ
deep learning model ⓘ image recognition model ⓘ |
| activationFunction |
sigmoid function
ⓘ
tanh function ⓘ |
| basedOn |
artificial neural networks
ⓘ
backpropagation ⓘ convolution operation ⓘ gradient descent ⓘ |
| developedAt |
Bell Telephone Laboratories
ⓘ
surface form:
AT&T Bell Labs
|
| developer |
Léon Bottou
ⓘ
Patrick Haffner ⓘ Yann LeCun ⓘ Yoshua Bengio ⓘ |
| field |
computer vision
ⓘ
deep learning ⓘ machine learning ⓘ pattern recognition ⓘ |
| hasComponent |
convolutional layer
ⓘ
fully connected layer ⓘ output layer ⓘ pooling layer ⓘ subsampling layer ⓘ |
| historicalSignificance |
one of the earliest successful CNNs
ⓘ
pioneered modern deep learning for vision ⓘ |
| influenced |
AlexNet
ⓘ
ResNet ⓘ VGG ⓘ modern CNN architectures ⓘ |
| inputDomain | 28x28 pixel images ⓘ |
| inputType | grayscale images ⓘ |
| learningParadigm | end-to-end learning ⓘ |
| lossFunction | cross-entropy loss ⓘ |
| notableDataset | MNIST ⓘ |
| notablePublication | Gradient-based learning applied to document recognition ⓘ |
| optimizationObjective | classification accuracy ⓘ |
| primaryTask |
bank check digit recognition
ⓘ
zip code recognition ⓘ |
| publicationYear | 1998 ⓘ |
| regularization | weight decay ⓘ |
| trainingMethod |
stochastic gradient descent
ⓘ
supervised learning ⓘ |
| usedFor |
handwritten digit recognition
ⓘ
image classification ⓘ optical character recognition ⓘ |
| yearProposed | 1989 ⓘ |
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: LeNet Description of subject: LeNet is one of the earliest convolutional neural network architectures, pioneering modern deep learning approaches to image recognition and handwritten digit classification.
Referenced by (5)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
LeNet-5 convolutional neural network (with Yann LeCun and others)