AmoebaNet
E899015
convolutional neural network architecture
image classification model
neural architecture search result
AmoebaNet is a convolutional neural network architecture discovered through evolutionary neural architecture search, known for achieving state-of-the-art image classification performance.
All labels observed (1)
| Label | Occurrences |
|---|---|
| AmoebaNet canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T11003094 — 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: AmoebaNet Context triple: [Neural Architecture Search, notableMethod, AmoebaNet]
-
A.
the Amplified Panatropic Computation Network
The Amplified Panatropic Computation Network is a vast, hyper-advanced Gallifreyan data and information processing system used by the Time Lords in the Doctor Who universe.
-
B.
Neural Architecture Search
Neural Architecture Search is an automated machine learning technique that uses algorithms to design and optimize neural network architectures without extensive human intervention.
-
C.
Horovod
Horovod is an open-source distributed deep learning framework designed to make training models across multiple GPUs and machines fast and easy.
-
D.
Learning Transferable Architectures for Scalable Image Recognition
"Learning Transferable Architectures for Scalable Image Recognition" is a research paper that introduced NASNet, a neural architecture search–designed convolutional network that achieved state-of-the-art performance on large-scale image recognition tasks.
-
E.
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.
- 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: AmoebaNet Target entity description: AmoebaNet is a convolutional neural network architecture discovered through evolutionary neural architecture search, known for achieving state-of-the-art image classification performance.
-
A.
the Amplified Panatropic Computation Network
The Amplified Panatropic Computation Network is a vast, hyper-advanced Gallifreyan data and information processing system used by the Time Lords in the Doctor Who universe.
-
B.
Neural Architecture Search
Neural Architecture Search is an automated machine learning technique that uses algorithms to design and optimize neural network architectures without extensive human intervention.
-
C.
Horovod
Horovod is an open-source distributed deep learning framework designed to make training models across multiple GPUs and machines fast and easy.
-
D.
Learning Transferable Architectures for Scalable Image Recognition
"Learning Transferable Architectures for Scalable Image Recognition" is a research paper that introduced NASNet, a neural architecture search–designed convolutional network that achieved state-of-the-art performance on large-scale image recognition tasks.
-
E.
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.
- F. None of above. chosen
Statements (47)
| Predicate | Object |
|---|---|
| instanceOf |
convolutional neural network architecture
ⓘ
image classification model ⓘ neural architecture search result ⓘ |
| applicationDomain |
image feature extraction
ⓘ
large-scale visual recognition ⓘ |
| architectureStyle |
cell-based CNN
ⓘ
multi-branch convolutional architecture ⓘ |
| basedOn | cell-based architecture search space ⓘ |
| benchmark |
CIFAR-10
NERFINISHED
ⓘ
CIFAR-100 NERFINISHED ⓘ ImageNet NERFINISHED ⓘ |
| comparedTo |
NASNet
NERFINISHED
ⓘ
PNASNet NERFINISHED ⓘ hand-designed CNN architectures ⓘ |
| developedBy |
Google
NERFINISHED
ⓘ
Google Brain NERFINISHED ⓘ |
| discoveredBy | Google Brain researchers NERFINISHED ⓘ |
| field |
computer vision
ⓘ
deep learning ⓘ machine learning ⓘ |
| framework | TensorFlow (original implementation) NERFINISHED ⓘ |
| hasProperty |
high top-1 accuracy on ImageNet
ⓘ
high top-5 accuracy on ImageNet ⓘ state-of-the-art performance on ImageNet at time of publication ⓘ |
| hasVariant |
AmoebaNet-A
NERFINISHED
ⓘ
AmoebaNet-B NERFINISHED ⓘ AmoebaNet-C NERFINISHED ⓘ |
| implementedWith |
ReLU nonlinearities
ⓘ
batch normalization ⓘ stochastic gradient descent ⓘ |
| influenced | later NAS-based CNN architectures ⓘ |
| introducedBy |
Alok Aggarwal
NERFINISHED
ⓘ
Esteban Real NERFINISHED ⓘ Quoc V. Le NERFINISHED ⓘ Yanping Huang NERFINISHED ⓘ |
| introducedIn | “Regularized Evolution for Image Classifier Architecture Search” NERFINISHED ⓘ |
| language | Python (typical implementation) ⓘ |
| optimizationObjective | validation accuracy ⓘ |
| publicationType | research paper ⓘ |
| searchAlgorithm |
aging evolution
ⓘ
evolutionary neural architecture search ⓘ |
| task | image classification ⓘ |
| usesTechnique |
convolutional neural networks
ⓘ
evolutionary algorithms ⓘ neural architecture search ⓘ regularized evolution ⓘ |
| yearOfIntroduction | 2018 ⓘ |
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: AmoebaNet Description of subject: AmoebaNet is a convolutional neural network architecture discovered through evolutionary neural architecture search, known for achieving state-of-the-art image classification performance.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.