Inception architecture
E107999
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.
All labels observed (11)
How this entity was disambiguated
This entity first appeared as the object of triple T921632 — 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: Inception architecture Context triple: [Christian Szegedy, notableWork, Inception architecture]
-
A.
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.
-
B.
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.
-
C.
“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.
-
D.
“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.
-
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: Inception architecture Target entity description: 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.
-
A.
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.
-
B.
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.
-
C.
“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.
-
D.
“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.
-
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 (48)
| Predicate | Object |
|---|---|
| instanceOf |
convolutional neural network architecture
ⓘ
deep learning model architecture ⓘ |
| achievedResult | won ILSVRC 2014 image classification challenge via GoogLeNet ⓘ |
| commonlyUsedWith |
ReLU activation functions
ⓘ
batch normalization ⓘ softmax output layer ⓘ |
| designPrinciple |
balancing depth and width of networks
ⓘ
computational cost optimization under fixed resource budget ⓘ multi-branch convolutional paths with different receptive field sizes ⓘ |
| developedAt | Google ⓘ |
| field |
computer vision
ⓘ
deep learning ⓘ machine learning ⓘ |
| goal |
achieve state-of-the-art image recognition performance
ⓘ
improve computational efficiency of deep CNNs ⓘ |
| hasKeyFeature |
1x1 convolutions for dimensionality reduction
ⓘ
Inception architecture self-linksurface differs ⓘ
surface form:
Inception modules
factorized convolutions ⓘ parallel multi-scale processing ⓘ sparse connections approximated by dense operations ⓘ |
| hasVariant |
Inception v1
ⓘ
Inception v2 ⓘ Inception architecture self-linksurface differs ⓘ
surface form:
Inception v3
Inception v4 ⓘ Inception architecture self-linksurface differs ⓘ
surface form:
Inception-ResNet
|
| influenced |
later efficient CNN architectures
ⓘ
multi-branch network designs ⓘ |
| inspiredBy | Network-in-Network architecture ⓘ |
| introducedBy |
Andrew Rabinovich
ⓘ
Christian Szegedy ⓘ Dragomir Anguelov ⓘ Dumitru Erhan ⓘ Pierre Sermanet ⓘ Scott Reed ⓘ Vincent Vanhoucke ⓘ Wei Liu ⓘ Yangqing Jia ⓘ |
| introducedIn | GoogLeNet ⓘ |
| introducedInPaper |
Inception architecture
self-linksurface differs
ⓘ
surface form:
Going Deeper with Convolutions
|
| notableProperty |
good accuracy–computation trade-off
ⓘ
scales well to large datasets like ImageNet ⓘ |
| optimizationMethod | stochastic gradient descent ⓘ |
| paperPublishedAt |
IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ⓘ
surface form:
CVPR 2015
|
| typicalInputDomain | natural images ⓘ |
| usedFor |
feature extraction
ⓘ
image classification ⓘ image recognition ⓘ object detection ⓘ |
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: Inception architecture Description of subject: 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.
Referenced by (16)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
Going Deeper with Convolutions
this entity surface form:
Rethinking the Inception Architecture for Computer Vision
this entity surface form:
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
this entity surface form:
GoogLeNet
this entity surface form:
Inception-based architectures
subject surface form:
torchvision
this entity surface form:
GoogLeNet
subject surface form:
torchvision
this entity surface form:
InceptionV3
this entity surface form:
Inception modules
this entity surface form:
Going Deeper with Convolutions
this entity surface form:
Inception v3
this entity surface form:
Inception-ResNet
this entity surface form:
Rethinking the Inception Architecture for Computer Vision
this entity surface form:
Inception network
this entity surface form:
Inception network