SOTAVerified

Neural Architecture Search

Neural architecture search (NAS) is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine learning. NAS essentially takes the process of a human manually tweaking a neural network and learning what works well, and automates this task to discover more complex architectures.

Image Credit : NAS with Reinforcement Learning

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1451–1475 of 1915 papers

TitleStatusHype
LETI: Latency Estimation Tool and Investigation of Neural Networks inference on Mobile GPU—0
Stochastic analysis of heterogeneous porous material with modified neural architecture search (NAS) based physics-informed neural networks using transfer learning—0
Neighbourhood Distillation: On the benefits of non end-to-end distillation—0
Effective Regularization Through Loss-Function Metalearning—0
MS-RANAS: Multi-Scale Resource-Aware Neural Architecture SearchCode0
A Surgery of the Neural Architecture Evaluators—0
Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search—0
Once Quantized for All: Progressively Searching for Quantized Compact Models—0
Disentangled Neural Architecture Search—0
Multi-Pass Transformer for Machine Translation—0
AutoRC: Improving BERT Based Relation Classification Models via Architecture Search—0
Using Neural Architecture Search for Improving Software Flaw Detection in Multimodal Deep Learning Models—0
Evolutionary Architecture Search for Graph Neural NetworksCode0
An Experimental Study of Weight Initialization and Weight Inheritance Effects on Neuroevolution—0
MSR-DARTS: Minimum Stable Rank of Differentiable Architecture SearchCode0
BNAS-v2: Memory-efficient and Performance-collapse-prevented Broad Neural Architecture Search—0
UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation—0
AutoML for Multilayer Perceptron and FPGA Co-design—0
DANCE: Differentiable Accelerator/Network Co-Exploration—0
Binarized Neural Architecture Search for Efficient Object Recognition—0
AutoKWS: Keyword Spotting with Differentiable Architecture Search—0
Real Image Super Resolution Via Heterogeneous Model Ensemble using GP-NAS—0
Boosting Share Routing for Multi-task Learning—0
Neural Architecture Search For Keyword Spotting—0
A Novel Training Protocol for Performance Predictors of Evolutionary Neural Architecture Search Algorithms—0
Show:102550
← PrevPage 59 of 77Next →
All datasetsImageNetNAS-Bench-201, ImageNet-16-120CIFAR-10NAS-Bench-201, CIFAR-100NAS-Bench-201, CIFAR-10CIFAR-10 Image ClassificationCIFAR-100NATS-Bench Topology, CIFAR-10NATS-Bench Topology, CIFAR-100NATS-Bench Topology, ImageNet16-120Food-101NAS-Bench-101

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SPOS (ProxylessNAS (GPU) latency)Accuracy75.3—Unverified
2SPOS (FBNet-C latency)Accuracy75.1—Unverified
3SPOS (block search + channel search)Accuracy74.7—Unverified
4MUXNet-xsTop-1 Error Rate33.3—Unverified
5FBNetV2-F1Top-1 Error Rate31.7—Unverified
6LayerNAS-60MTop-1 Error Rate31—Unverified
7NASGEPTop-1 Error Rate29.51—Unverified
8MUXNet-sTop-1 Error Rate28.4—Unverified
9NN-MASS-ATop-1 Error Rate27.1—Unverified
10FBNetV2-F3Top-1 Error Rate26.8—Unverified
#ModelMetricClaimedVerifiedStatus
1CR-LSOAccuracy (Test)46.98—Unverified
2Shapley-NASAccuracy (Test)46.85—Unverified
3β-SDARTS-RSAccuracy (Test)46.71—Unverified
4β-RDARTS-L2Accuracy (Test)46.71—Unverified
5ASE-NAS+Accuracy (Val)46.66—Unverified
6NARAccuracy (Test)46.66—Unverified
7BaLeNAS-TFAccuracy (Test)46.54—Unverified
8AG-NetAccuracy (Test)46.42—Unverified
9Local searchAccuracy (Test)46.38—Unverified
10NASBOTAccuracy (Test)46.37—Unverified
#ModelMetricClaimedVerifiedStatus
1Balanced MixtureAccuracy (% )91.55—Unverified
2GDASTop-1 Error Rate3.4—Unverified
3Bonsai-NetTop-1 Error Rate3.35—Unverified
4Net2 (2)Top-1 Error Rate3.3—Unverified
5μDARTSTop-1 Error Rate3.28—Unverified
6NN-MASS- CIFAR-CTop-1 Error Rate3.18—Unverified
7DARTS (first order)Top-1 Error Rate3—Unverified
8NN-MASS- CIFAR-ATop-1 Error Rate3—Unverified
9AlphaX-1 (cutout NASNet)Top-1 Error Rate2.82—Unverified
10NASGEPTop-1 Error Rate2.82—Unverified