|
gptkbp:instance_of
|
gptkb:neural_networks
|
|
gptkbp:architecture
|
gptkb:neural_networks
|
|
gptkbp:based_on
|
gptkb:Neural_Architecture_Search
|
|
gptkbp:coat_of_arms
|
Fully Connected Layer
Skip Connections
Residual Blocks
|
|
gptkbp:competes_with
|
gptkb:Efficient_Net
gptkb:Dense_Net
gptkb:Res_Net
|
|
gptkbp:contains
|
Convolutional Layers
Pooling Layers
Activation Functions
|
|
gptkbp:designed_for
|
Automated Neural Architecture Search
|
|
gptkbp:developed_by
|
gptkb:Google
|
|
gptkbp:has_achieved
|
State-of-the-art performance
|
|
gptkbp:has_function
|
Over 88 million parameters
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
NASNet-C
|
|
gptkbp:improves
|
Model Efficiency
|
|
gptkbp:influenced_by
|
gptkb:Mobile_Net
gptkb:Inception_Network
gptkb:Xception
|
|
gptkbp:introduced_in
|
gptkb:2018
|
|
gptkbp:is_evaluated_by
|
gptkb:Image_Net
gptkb:CIFAR-10
Inference Time
Top-1 and Top-5 Accuracy Metrics
FLOPs (Floating Point Operations)
|
|
gptkbp:is_optimized_for
|
gptkb:mobile_devices
Real-time Applications
|
|
gptkbp:is_part_of
|
gptkb:AI_Research
Deep Learning Community
|
|
gptkbp:is_related_to
|
gptkb:Artificial_Intelligence
Deep Learning Frameworks
Hyperparameter Optimization
Computer Vision Tasks
Neural Architecture Search Algorithms
|
|
gptkbp:is_supported_by
|
gptkb:Tensor_Flow
gptkb:Keras
gptkb:Py_Torch
|
|
gptkbp:is_used_in
|
gptkb:Autonomous_Vehicles
Object Detection
Facial Recognition
Medical Imaging
Video Analysis
|
|
gptkbp:performance
|
Top-1 accuracy of 82.7% on Image Net
Top-5 accuracy of 95.2% on Image Net
|
|
gptkbp:predecessor
|
gptkb:NASNet-A
|
|
gptkbp:published_in
|
gptkb:CVPR_2018
|
|
gptkbp:requires
|
Large Computational Resources
|
|
gptkbp:successor
|
gptkb:NASNet
|
|
gptkbp:supports
|
gptkb:stage_adaptation
|
|
gptkbp:used_for
|
Image Classification
|
|
gptkbp:uses
|
gptkb:machine_learning
|
|
gptkbp:utilizes
|
gptkb:Batch_Normalization
Dropout Regularization
|
|
gptkbp:bfsParent
|
gptkb:NASNet
|
|
gptkbp:bfsLayer
|
6
|