GoogLeNet
E472885
GoogLeNet is a deep convolutional neural network developed by Google that popularized the Inception architecture and achieved state-of-the-art performance in image recognition tasks.
All labels observed (3)
| Label | Occurrences |
|---|---|
| GoogLeNet canonical | 5 |
| GoogLeNet Inception architecture | 1 |
| GoogLeNet architecture | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T4833460 — 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: GoogLeNet Context triple: [Inception architecture, introducedIn, GoogLeNet]
-
A.
SqueezeNet
SqueezeNet is a compact deep convolutional neural network architecture designed to achieve AlexNet-level image classification accuracy with dramatically fewer parameters, making it efficient for deployment on resource-constrained devices.
-
B.
VGG
VGG is a deep convolutional neural network architecture known for its simple, uniform use of small 3×3 filters and great depth, which achieved strong performance in image recognition tasks.
-
C.
ResNet
ResNet is a deep convolutional neural network architecture known for its use of residual connections to enable very deep models and achieve state-of-the-art performance in image recognition tasks.
-
D.
AlexNet
AlexNet is a pioneering deep convolutional neural network architecture that dramatically advanced image recognition performance and helped spark the modern deep learning revolution after winning the 2012 ImageNet competition.
-
E.
LeNet
LeNet is one of the earliest convolutional neural network architectures, pioneering modern deep learning approaches to image recognition and handwritten digit classification.
- 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: GoogLeNet Target entity description: GoogLeNet is a deep convolutional neural network developed by Google that popularized the Inception architecture and achieved state-of-the-art performance in image recognition tasks.
-
A.
SqueezeNet
SqueezeNet is a compact deep convolutional neural network architecture designed to achieve AlexNet-level image classification accuracy with dramatically fewer parameters, making it efficient for deployment on resource-constrained devices.
-
B.
VGG
VGG is a deep convolutional neural network architecture known for its simple, uniform use of small 3×3 filters and great depth, which achieved strong performance in image recognition tasks.
-
C.
ResNet
ResNet is a deep convolutional neural network architecture known for its use of residual connections to enable very deep models and achieve state-of-the-art performance in image recognition tasks.
-
D.
AlexNet
AlexNet is a pioneering deep convolutional neural network architecture that dramatically advanced image recognition performance and helped spark the modern deep learning revolution after winning the 2012 ImageNet competition.
-
E.
LeNet
LeNet is one of the earliest convolutional neural network architectures, pioneering modern deep learning approaches to image recognition and handwritten digit classification.
- F. None of above. chosen
Statements (49)
| Predicate | Object |
|---|---|
| instanceOf |
convolutional neural network architecture
ⓘ
deep learning model ⓘ image classification model ⓘ |
| achieved | state-of-the-art performance on ImageNet ⓘ |
| alsoKnownAs | Inception v1 ⓘ |
| architectureType | multi-branch convolutional network ⓘ |
| award | winner of ILSVRC 2014 classification challenge ⓘ |
| basedOn | Inception architecture ⓘ |
| competition |
ILSVRC 2014
ⓘ
linked to:
ImageNet
|
| dataset | ImageNet ⓘ |
| designGoal |
improve computational efficiency
ⓘ
increase depth and width without large parameter growth ⓘ |
| developer |
Google
ⓘ
Google Research ⓘ |
| domain | large-scale visual recognition ⓘ |
| field |
computer vision
ⓘ
deep learning ⓘ |
| framework |
Caffe
ⓘ
PyTorch ⓘ TensorFlow ⓘ |
| influencedBy | Network-in-Network architecture ⓘ |
| inputResolution | 224x224 pixels ⓘ |
| inspired |
Inception v2
ⓘ
Inception v3 ⓘ
linked to:
Inception architecture
Inception v4 ⓘ Inception-ResNet ⓘ
linked to:
Inception architecture
later Inception variants ⓘ |
| introducedInPaper |
Going Deeper with Convolutions
ⓘ
linked to:
Inception architecture
|
| numberOfLayers | 22 ⓘ |
| numberOfParameters | about 5 million ⓘ |
| optimizationMethod | stochastic gradient descent ⓘ |
| paperTitle |
Going Deeper with Convolutions
ⓘ
linked to:
Inception architecture
|
| paperVenue | CVPR 2015 ⓘ |
| regularization |
data augmentation
ⓘ
dropout ⓘ |
| task |
image classification
ⓘ
image recognition ⓘ object recognition ⓘ |
| top5ErrorRate | 6.67% ⓘ |
| uses |
1x1 convolutions
ⓘ
3x3 convolutions ⓘ 5x5 convolutions ⓘ Inception modules ⓘ
linked to:
Inception architecture
ReLU activation functions ⓘ auxiliary classifiers ⓘ average pooling ⓘ global average pooling before final layer ⓘ max pooling ⓘ |
| yearIntroduced | 2014 ⓘ |
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: GoogLeNet Description of subject: GoogLeNet is a deep convolutional neural network developed by Google that popularized the Inception architecture and achieved state-of-the-art performance in image recognition tasks.
Referenced by (7)
Full triples — surface form annotated when it differs from this entity's canonical label.
linked to: GoogLeNet
linked to: GoogLeNet