Network-in-Network architecture
E472886
convolutional neural network architecture
deep learning model architecture
image classification architecture
Network-in-Network architecture is a convolutional neural network design that replaces traditional linear convolution layers with micro multilayer perceptrons (MLPs) to enhance feature abstraction and model expressiveness.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Network-in-Network architecture canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T4833480 — 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: Network-in-Network architecture Context triple: [Inception architecture, inspiredBy, Network-in-Network architecture]
-
A.
Towards a New Architecture
Towards a New Architecture is a seminal 1923 architectural treatise by Le Corbusier that advocates for modernist design principles grounded in industrialization, functionalism, and new construction technologies.
-
B.
Classless Inter-Domain Routing
Classless Inter-Domain Routing (CIDR) is an IP addressing and routing scheme that replaces traditional class-based networks to enable more efficient allocation of IP address space and improved route aggregation on the internet.
-
C.
Internet architecture
Internet architecture is the overarching design framework and set of principles that define how the global network of interconnected computer systems and protocols operates and evolves.
-
D.
Requirements for Internet Hosts – Communication Layers
"Requirements for Internet Hosts – Communication Layers" is an IETF standards document (RFC 1122) that specifies the protocol and behavior requirements for Internet host communication across the network, transport, and related layers.
-
E.
ARPANET Interface Message Processor platform
The ARPANET Interface Message Processor platform was the specialized packet-switching computer system that formed the backbone of the early ARPANET, handling data routing between host machines in the first large-scale packet-switched network.
- 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: Network-in-Network architecture Target entity description: Network-in-Network architecture is a convolutional neural network design that replaces traditional linear convolution layers with micro multilayer perceptrons (MLPs) to enhance feature abstraction and model expressiveness.
-
A.
Towards a New Architecture
Towards a New Architecture is a seminal 1923 architectural treatise by Le Corbusier that advocates for modernist design principles grounded in industrialization, functionalism, and new construction technologies.
-
B.
Classless Inter-Domain Routing
Classless Inter-Domain Routing (CIDR) is an IP addressing and routing scheme that replaces traditional class-based networks to enable more efficient allocation of IP address space and improved route aggregation on the internet.
-
C.
Internet architecture
Internet architecture is the overarching design framework and set of principles that define how the global network of interconnected computer systems and protocols operates and evolves.
-
D.
Requirements for Internet Hosts – Communication Layers
"Requirements for Internet Hosts – Communication Layers" is an IETF standards document (RFC 1122) that specifies the protocol and behavior requirements for Internet host communication across the network, transport, and related layers.
-
E.
ARPANET Interface Message Processor platform
The ARPANET Interface Message Processor platform was the specialized packet-switching computer system that formed the backbone of the early ARPANET, handling data routing between host machines in the first large-scale packet-switched network.
- F. None of above. chosen
Statements (45)
| Predicate | Object |
|---|---|
| instanceOf |
convolutional neural network architecture
ⓘ
deep learning model architecture ⓘ image classification architecture ⓘ |
| aimsTo |
enhance feature abstraction
ⓘ
improve classification performance ⓘ increase model expressiveness ⓘ |
| basedOn | convolutional neural networks ⓘ |
| characterizedBy |
end-to-end training with backpropagation
ⓘ
nonlinear feature mapping within receptive fields ⓘ parameter efficiency compared to large fully connected layers ⓘ |
| citationTitle | Network In Network NERFINISHED ⓘ |
| domain |
computer vision
ⓘ
deep learning research ⓘ |
| evaluatedOn |
CIFAR-10
NERFINISHED
ⓘ
CIFAR-100 NERFINISHED ⓘ ImageNet (ILSVRC-2012 subset) NERFINISHED ⓘ SVHN NERFINISHED ⓘ |
| hasKeyIdea |
perform classification with global average pooling instead of fully connected layers
ⓘ
replace linear filters with small neural networks ⓘ |
| improvesUpon | AlexNet-style CNNs NERFINISHED ⓘ |
| includesLayerType |
convolutional layers
ⓘ
global average pooling layers ⓘ mlpconv layers ⓘ pooling layers ⓘ |
| influenced |
Inception architecture
NERFINISHED
ⓘ
design of fully convolutional networks ⓘ use of 1x1 convolutions in later CNNs ⓘ |
| introduces |
global average pooling as a replacement for fully connected layers
ⓘ
mlpconv layers ⓘ |
| optimizationMethod | stochastic gradient descent ⓘ |
| outputType | class probabilities ⓘ |
| proposedBy |
Min Lin
NERFINISHED
ⓘ
Qiang Chen NERFINISHED ⓘ Shuicheng Yan NERFINISHED ⓘ |
| publicationYear | 2013 ⓘ |
| publishedIn | arXiv:1312.4400 ⓘ |
| reduces | overfitting compared to large fully connected layers ⓘ |
| replaces | linear convolution layers with micro multilayer perceptrons ⓘ |
| trainingDataType | labeled images ⓘ |
| uses |
1x1 convolutions
ⓘ
global average pooling ⓘ micro multilayer perceptrons ⓘ |
| usesActivationFunction | ReLU NERFINISHED ⓘ |
| 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: Network-in-Network architecture Description of subject: Network-in-Network architecture is a convolutional neural network design that replaces traditional linear convolution layers with micro multilayer perceptrons (MLPs) to enhance feature abstraction and model expressiveness.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.