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 1851–1900 of 1915 papers

TitleStatusHype
Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource UtilizationCode0
Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search—0
TEA-DNN: the Quest for Time-Energy-Accuracy Co-optimized Deep Neural Networks—0
InstaNAS: Instance-aware Neural Architecture SearchCode0
GP-CNAS: Convolutional Neural Network Architecture Search with Genetic Programming—0
Evolutionary-Neural Hybrid Agents for Architecture Search—0
Joint Neural Architecture Search and Quantization—0
Deep Active Learning with a Neural Architecture SearchCode0
Stochastic Adaptive Neural Architecture Search for Keyword SpottingCode0
You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse OptimizationCode0
Automated Machine Learning: From Principles to PracticesCode0
The CoSTAR Block Stacking Dataset: Learning with Workspace ConstraintsCode0
Rethinking the Value of Network PruningCode0
NSGA-Net: Neural Architecture Search using Multi-Objective Genetic AlgorithmCode0
NSGA-Net: A Multi-Objective Genetic Algorithm for Neural Architecture Search—0
Exploring Shared Structures and Hierarchies for Multiple NLP Tasks—0
Neural Architecture OptimizationCode0
Neural Architecture Search: A SurveyCode0
Teacher Guided Architecture Search—0
Efficient Progressive Neural Architecture Search—0
Reinforced Evolutionary Neural Architecture SearchCode0
MaskConnect: Connectivity Learning by Gradient Descent—0
BAM: Bottleneck Attention ModuleCode0
Understanding and Simplifying One-Shot Architecture Search—0
OpenNMT System Description for WNMT 2018: 800 words/sec on a single-core CPU—0
Efficient Neural Architecture Search via Parameters Sharing—0
MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning—0
Auto-Keras: An Efficient Neural Architecture Search SystemCode0
Resource-Efficient Neural Architect—0
Auto-Meta: Automated Gradient Based Meta Learner Search—0
Path-Level Network Transformation for Efficient Architecture SearchCode0
TAPAS: Train-less Accuracy Predictor for Architecture Search—0
Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution—0
GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning—0
Generalized Hadamard-Product Fusion Operators for Visual Question Answering—0
Fast Neural Architecture Construction using EnvelopeNets—0
Evolutionary Architecture Search For Deep Multitask Networks—0
Transfer Learning with Neural AutoML—0
Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency AnalysisCode0
Neural Architecture Search with Bayesian Optimisation and Optimal TransportCode0
Regularized Evolution for Image Classifier Architecture SearchCode0
GitGraph - Architecture Search Space Creation through Frequent Computational Subgraph Mining—0
AMLA: an AutoML frAmework for Neural Network Design—0
EXPLORING NEURAL ARCHITECTURE SEARCH FOR LANGUAGE TASKS—0
Faster Discovery of Neural Architectures by Searching for Paths in a Large Model—0
Finding Competitive Network Architectures Within a Day Using UCT—0
A Flexible Approach to Automated RNN Architecture Generation—0
Progressive Neural Architecture SearchCode0
Deep Learning Scaling is Predictable, Empirically—0
Simple And Efficient Architecture Search for Convolutional Neural NetworksCode0
Show:102550
← PrevPage 38 of 39Next →
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-RDARTS-L2Accuracy (Test)46.71—Unverified
4β-SDARTS-RSAccuracy (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
7NN-MASS- CIFAR-ATop-1 Error Rate3—Unverified
8DARTS (first order)Top-1 Error Rate3—Unverified
9NASGEPTop-1 Error Rate2.82—Unverified
10AlphaX-1 (cutout NASNet)Top-1 Error Rate2.82—Unverified