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.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (1)

Label	Occurrences
AmoebaNet canonical	1

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 ⓘ

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.

Neural Architecture Search → notableMethod → AmoebaNet ⓘ