ImageNet Classification with Deep Convolutional Neural Networks
E554013
"ImageNet Classification with Deep Convolutional Neural Networks" is the landmark 2012 research paper that introduced the deep CNN model AlexNet, demonstrating a dramatic leap in image recognition performance on the ImageNet benchmark and catalyzing the modern deep learning revolution in computer vision.
All labels observed (1)
| Label | Occurrences |
|---|---|
| ImageNet Classification with Deep Convolutional Neural Networks canonical | 2 |
How this entity was disambiguated
This entity first appeared as the object of triple T5910819 — 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: ImageNet Classification with Deep Convolutional Neural Networks Context triple: [Alex Krizhevsky, coAuthorOf, ImageNet Classification with Deep Convolutional Neural Networks]
-
A.
Very Deep Convolutional Networks for Large-Scale Image Recognition
"Very Deep Convolutional Networks for Large-Scale Image Recognition" is the influential 2014 research paper that introduced the VGG family of deep convolutional neural network architectures, demonstrating that significantly increasing network depth with small convolutional filters leads to substantial improvements in image classification performance.
-
B.
Inception architecture
The Inception architecture is a deep convolutional neural network design that introduced parallel multi-scale processing modules to achieve state-of-the-art image recognition performance with improved computational efficiency.
-
C.
Long-term Recurrent Convolutional Networks for Visual Recognition and Description
"Long-term Recurrent Convolutional Networks for Visual Recognition and Description" is a research paper that introduces a deep learning architecture combining convolutional and recurrent neural networks to perform tasks like video recognition and automatic image or video captioning.
-
D.
Large-Scale Distributed Deep Networks
Large-Scale Distributed Deep Networks is a seminal research work that introduced methods for training deep neural networks efficiently across large-scale distributed computing infrastructure, enabling breakthroughs in modern large-scale AI systems.
-
E.
“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.
- 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: ImageNet Classification with Deep Convolutional Neural Networks Target entity description: "ImageNet Classification with Deep Convolutional Neural Networks" is the landmark 2012 research paper that introduced the deep CNN model AlexNet, demonstrating a dramatic leap in image recognition performance on the ImageNet benchmark and catalyzing the modern deep learning revolution in computer vision.
-
A.
Very Deep Convolutional Networks for Large-Scale Image Recognition
"Very Deep Convolutional Networks for Large-Scale Image Recognition" is the influential 2014 research paper that introduced the VGG family of deep convolutional neural network architectures, demonstrating that significantly increasing network depth with small convolutional filters leads to substantial improvements in image classification performance.
-
B.
Inception architecture
The Inception architecture is a deep convolutional neural network design that introduced parallel multi-scale processing modules to achieve state-of-the-art image recognition performance with improved computational efficiency.
-
C.
Long-term Recurrent Convolutional Networks for Visual Recognition and Description
"Long-term Recurrent Convolutional Networks for Visual Recognition and Description" is a research paper that introduces a deep learning architecture combining convolutional and recurrent neural networks to perform tasks like video recognition and automatic image or video captioning.
-
D.
Large-Scale Distributed Deep Networks
Large-Scale Distributed Deep Networks is a seminal research work that introduced methods for training deep neural networks efficiently across large-scale distributed computing infrastructure, enabling breakthroughs in modern large-scale AI systems.
-
E.
“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.
- F. None of above. chosen
Statements (48)
| Predicate | Object |
|---|---|
| instanceOf |
computer vision paper
ⓘ
research paper ⓘ |
| benchmark |
ILSVRC-2010
NERFINISHED
ⓘ
ILSVRC-2012 ⓘ |
| considered |
catalyst of the deep learning revolution in vision
ⓘ
landmark paper in deep learning ⓘ |
| field |
computer vision
ⓘ
deep learning ⓘ machine learning ⓘ |
| focusesOn | image classification ⓘ |
| hasAbbreviation | AlexNet NERFINISHED ⓘ |
| hasAuthor |
Alex Krizhevsky
NERFINISHED
ⓘ
Geoffrey E. Hinton NERFINISHED ⓘ Ilya Sutskever NERFINISHED ⓘ |
| hasCitationVenueAbbreviation | NIPS 2012 NERFINISHED ⓘ |
| hasShortName | AlexNet paper NERFINISHED ⓘ |
| improvementOverStateOfTheArtTop5Error | more than 10 percentage points ⓘ |
| influencedField |
large-scale neural network training on GPUs
ⓘ
modern deep learning in computer vision ⓘ |
| inputImageResolution | 224x224 pixels ⓘ |
| introducesModel | AlexNet NERFINISHED ⓘ |
| introducesTechnique |
ReLU nonlinearity in large-scale vision CNNs
ⓘ
data augmentation for image classification ⓘ dropout for fully connected layers ⓘ local response normalization ⓘ overlapping max pooling ⓘ |
| language | English ⓘ |
| numberOfConvolutionalLayersInModel | 5 ⓘ |
| numberOfFullyConnectedLayersInModel | 3 ⓘ |
| numberOfLayersInModel | 8 ⓘ |
| parallelizationStrategy | model parallelism across two GPUs ⓘ |
| presentedAt | NeurIPS 2012 NERFINISHED ⓘ |
| proposesArchitectureType | deep convolutional neural network ⓘ |
| publicationYear | 2012 ⓘ |
| publishedIn | Advances in Neural Information Processing Systems 25 NERFINISHED ⓘ |
| task | ImageNet Large Scale Visual Recognition Challenge classification NERFINISHED ⓘ |
| top5ErrorRateOnILSVRC2012 | 15.3% ⓘ |
| usesActivationFunction | ReLU ⓘ |
| usesDataAugmentation |
RGB intensity alterations
ⓘ
horizontal reflections ⓘ random crops ⓘ |
| usesDataset | ImageNet NERFINISHED ⓘ |
| usesHardware |
GPU
ⓘ
NVIDIA GTX 580 NERFINISHED ⓘ |
| usesNumberOfGPUs | 2 ⓘ |
| usesOptimizationAlgorithm | stochastic gradient descent ⓘ |
| usesRegularization |
dropout
ⓘ
weight decay ⓘ |
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: ImageNet Classification with Deep Convolutional Neural Networks Description of subject: "ImageNet Classification with Deep Convolutional Neural Networks" is the landmark 2012 research paper that introduced the deep CNN model AlexNet, demonstrating a dramatic leap in image recognition performance on the ImageNet benchmark and catalyzing the modern deep learning revolution in computer vision.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.