matching networks
E899063
Matching networks are a neural network architecture designed to perform one-shot learning by leveraging metric-based comparisons between support and query examples.
All labels observed (1)
| Label | Occurrences |
|---|---|
| matching networks canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T11003615 — 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 Context triple: [Matching Networks for One Shot Learning, introducesConcept, matching networks]
-
A.
Penjaringan
Penjaringan is a coastal subdistrict in North Jakarta, Indonesia, known for its fishing communities, ports, and low-lying areas prone to flooding.
-
B.
Mutual Network
Mutual Network was a major American radio network that operated throughout much of the 20th century, known for its news, entertainment programs, and nationwide affiliates.
-
C.
communication nets
Communication nets are interconnected systems of nodes and links that enable the transmission, routing, and exchange of messages or data across distributed components.
-
D.
MIMO
MIMO (Multiple-Input Multiple-Output) is a wireless communication technique that uses multiple transmitting and receiving antennas to significantly increase data throughput and link reliability.
-
E.
E-band systems
E-band systems are high-frequency millimeter-wave communication platforms operating roughly in the 60–90 GHz range, commonly used for high-capacity wireless backhaul and point-to-point links.
- 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 Target entity description: Matching networks are a neural network architecture designed to perform one-shot learning by leveraging metric-based comparisons between support and query examples.
-
A.
Penjaringan
Penjaringan is a coastal subdistrict in North Jakarta, Indonesia, known for its fishing communities, ports, and low-lying areas prone to flooding.
-
B.
Mutual Network
Mutual Network was a major American radio network that operated throughout much of the 20th century, known for its news, entertainment programs, and nationwide affiliates.
-
C.
communication nets
Communication nets are interconnected systems of nodes and links that enable the transmission, routing, and exchange of messages or data across distributed components.
-
D.
MIMO
MIMO (Multiple-Input Multiple-Output) is a wireless communication technique that uses multiple transmitting and receiving antennas to significantly increase data throughput and link reliability.
-
E.
E-band systems
E-band systems are high-frequency millimeter-wave communication platforms operating roughly in the 60–90 GHz range, commonly used for high-capacity wireless backhaul and point-to-point links.
- F. None of above. chosen
Statements (39)
| Predicate | Object |
|---|---|
| instanceOf |
few-shot learning method
ⓘ
metric-based meta-learning method ⓘ neural network architecture ⓘ |
| advantage | good performance with very few labeled examples ⓘ |
| appliedTo |
Omniglot dataset
ⓘ
image classification ⓘ miniImageNet dataset NERFINISHED ⓘ |
| category | non-parametric prediction over support set ⓘ |
| citationYear | 2016 ⓘ |
| coreIdea | classify queries by comparing them to labeled support examples in an embedding space ⓘ |
| designedFor |
few-shot classification
ⓘ
one-shot learning ⓘ |
| developedAt | DeepMind NERFINISHED ⓘ |
| evaluationProtocol | N-way K-shot classification episodes ⓘ |
| handles | variable-sized support sets ⓘ |
| inputIncludes |
query set
ⓘ
support set ⓘ |
| inspired | subsequent metric-based few-shot methods ⓘ |
| introducedInPaper | Matching Networks for One Shot Learning NERFINISHED ⓘ |
| keyComponent |
attention-based classifier
ⓘ
embedding network for query examples ⓘ embedding network for support examples ⓘ |
| learningType | supervised learning ⓘ |
| optimization | trained end-to-end with gradient descent ⓘ |
| outputs | label distribution over support set labels ⓘ |
| proposedBy |
Charles Blundell
NERFINISHED
ⓘ
Daan Wierstra NERFINISHED ⓘ Oriol Vinyals NERFINISHED ⓘ Timothy Lillicrap NERFINISHED ⓘ |
| publishedAtConference | NeurIPS 2016 NERFINISHED ⓘ |
| relatedTo |
Prototypical Networks
NERFINISHED
ⓘ
Siamese networks NERFINISHED ⓘ meta-learning ⓘ |
| trainingParadigm | episodic training ⓘ |
| uses |
attention kernel over support embeddings
ⓘ
attention mechanism ⓘ cosine similarity ⓘ embedding functions ⓘ metric-based comparisons ⓘ |
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 Description of subject: Matching networks are a neural network architecture designed to perform one-shot learning by leveraging metric-based comparisons between support and query examples.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.