Matching Networks for One Shot Learning
E260058
"Matching Networks for One Shot Learning" is a seminal deep learning paper that introduced a metric-based approach for one-shot image classification using attention and memory-augmented neural networks.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Matching Networks for One Shot Learning canonical | 4 |
How this entity was disambiguated
This entity first appeared as the object of triple T2373762 — 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: Matching Networks for One Shot Learning Context triple: [Oriol Vinyals, notableWork, Matching Networks for One Shot Learning]
-
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.
Adam: A Method for Stochastic Optimization
"Adam: A Method for Stochastic Optimization" is a highly influential machine learning paper that introduces the Adam optimizer, a widely used adaptive gradient-based optimization algorithm for training deep neural networks.
-
C.
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.
-
D.
Intriguing properties of neural networks
"Intriguing properties of neural networks" is a highly influential research paper that revealed surprising vulnerabilities and behaviors of deep neural networks, particularly their susceptibility to adversarial examples.
-
E.
Gradient-based learning applied to document recognition
"Gradient-based learning applied to document recognition" is a seminal 1998 paper by Yann LeCun and colleagues that introduced and demonstrated the effectiveness of convolutional neural networks for tasks like handwritten digit recognition, helping to lay the foundations of modern 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: Matching Networks for One Shot Learning Target entity description: "Matching Networks for One Shot Learning" is a seminal deep learning paper that introduced a metric-based approach for one-shot image classification using attention and memory-augmented neural networks.
-
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.
Adam: A Method for Stochastic Optimization
"Adam: A Method for Stochastic Optimization" is a highly influential machine learning paper that introduces the Adam optimizer, a widely used adaptive gradient-based optimization algorithm for training deep neural networks.
-
C.
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.
-
D.
Intriguing properties of neural networks
"Intriguing properties of neural networks" is a highly influential research paper that revealed surprising vulnerabilities and behaviors of deep neural networks, particularly their susceptibility to adversarial examples.
-
E.
Gradient-based learning applied to document recognition
"Gradient-based learning applied to document recognition" is a seminal 1998 paper by Yann LeCun and colleagues that introduced and demonstrated the effectiveness of convolutional neural networks for tasks like handwritten digit recognition, helping to lay the foundations of modern deep learning.
- F. None of above. chosen
Statements (48)
| Predicate | Object |
|---|---|
| instanceOf |
deep learning paper
ⓘ
machine learning paper ⓘ scientific paper ⓘ |
| affiliationOfAuthors | DeepMind ⓘ |
| approachType | metric-based few-shot learning ⓘ |
| architectureCharacteristic |
end-to-end differentiable
ⓘ
non-parametric prediction conditioned on support set ⓘ |
| citationType | highly cited paper ⓘ |
| contribution | demonstrated strong performance on one-shot learning benchmarks ⓘ |
| coreIdea |
combine metric learning with memory-augmented neural networks
ⓘ
learn a mapping from a support set to a classifier for one-shot learning ⓘ use attention over a support set to classify query examples ⓘ |
| datasetUsed |
Omniglot
ⓘ
miniImageNet ⓘ |
| evaluationProtocol | N-way K-shot classification ⓘ |
| field |
deep learning
ⓘ
few-shot learning ⓘ machine learning ⓘ one-shot learning ⓘ |
| firstAuthor | Oriol Vinyals ⓘ |
| hasAuthor |
Charles Blundell
ⓘ
Daan Wierstra ⓘ Koray Kavukcuoglu ⓘ Oriol Vinyals ⓘ Timothy Lillicrap ⓘ |
| influenced |
Prototypical Networks
ⓘ
Relation Networks for few-shot learning ⓘ meta-learning approaches for few-shot classification ⓘ |
| introducesConcept |
fully differentiable nearest-neighbor classifier
ⓘ
matching networks ⓘ |
| learningParadigm |
meta-learning for supervised tasks
ⓘ
supervised learning ⓘ |
| objective | maximize log-likelihood of correct labels given support set and query ⓘ |
| organization |
Google DeepMind
ⓘ
linked to:
DeepMind
|
| publishedIn |
Advances in Neural Information Processing Systems
ⓘ
linked to:
NeurIPS
NeurIPS 2016 ⓘ
linked to:
NeurIPS
|
| publisher |
Neural Information Processing Systems Foundation
ⓘ
linked to:
NeurIPS
|
| researchArea |
image classification
ⓘ
meta-learning ⓘ metric learning ⓘ |
| task |
few-shot image classification
ⓘ
one-shot image classification ⓘ |
| title | Matching Networks for One Shot Learning ⓘ |
| usesMethod |
attention mechanism
ⓘ
cosine similarity ⓘ embedding functions for images ⓘ memory-augmented neural networks ⓘ |
| year | 2016 ⓘ |
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: Matching Networks for One Shot Learning Description of subject: "Matching Networks for One Shot Learning" is a seminal deep learning paper that introduced a metric-based approach for one-shot image classification using attention and memory-augmented neural networks.
Referenced by (4)
Full triples — surface form annotated when it differs from this entity's canonical label.