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

Showing 751775 of 1915 papers

TitleStatusHype
i-Razor: A Differentiable Neural Input Razor for Feature Selection and Dimension Search in DNN-Based Recommender SystemsCode0
Neural Architecture Search for Speech Emotion Recognition0
Quasi-orthogonality and intrinsic dimensions as measures of learning and generalisation0
AutoCoMet: Smart Neural Architecture Search via Co-Regulated Shaping Reinforcement0
Nix-TTS: Lightweight and End-to-End Text-to-Speech via Module-wise DistillationCode2
Generalizing Few-Shot NAS with Gradient MatchingCode1
Robust and Energy-efficient PPG-based Heart-Rate Monitoring0
Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?Code0
AutoTS: Automatic Time Series Forecasting Model Design Based on Two-Stage Pruning0
A Semi-Decoupled Approach to Fast and Optimal Hardware-Software Co-Design of Neural AcceleratorsCode0
An Intelligent End-to-End Neural Architecture Search Framework for Electricity Forecasting Model Development0
EmotionNAS: Two-stream Neural Architecture Search for Speech Emotion Recognition0
Q-PPG: Energy-Efficient PPG-based Heart Rate Monitoring on Wearable DevicesCode1
U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture SearchCode0
PACE: A Parallelizable Computation Encoder for Directed Acyclic GraphsCode1
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot LearningCode1
DATA: Domain-Aware and Task-Aware Self-supervised LearningCode1
Progressive Subsampling for Oversampled Data -- Application to Quantitative MRICode0
On Redundancy and Diversity in Cell-based Neural Architecture SearchCode0
Learning Where To Look -- Generative NAS is Surprisingly EfficientCode1
Meta-Learning of NAS for Few-shot Learning in Medical Image Applications0
TAS: Ternarized Neural Architecture Search for Resource-Constrained Edge DevicesCode0
Less is More: Proxy Datasets in NAS approachesCode0
Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond0
Towards Less Constrained Macro-Neural Architecture SearchCode1
Show:102550
← PrevPage 31 of 77Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SPOS (ProxylessNAS (GPU) latency)Accuracy75.3Unverified
2SPOS (FBNet-C latency)Accuracy75.1Unverified
3SPOS (block search + channel search)Accuracy74.7Unverified
4MUXNet-xsTop-1 Error Rate33.3Unverified
5FBNetV2-F1Top-1 Error Rate31.7Unverified
6LayerNAS-60MTop-1 Error Rate31Unverified
7NASGEPTop-1 Error Rate29.51Unverified
8MUXNet-sTop-1 Error Rate28.4Unverified
9NN-MASS-ATop-1 Error Rate27.1Unverified
10FBNetV2-F3Top-1 Error Rate26.8Unverified
#ModelMetricClaimedVerifiedStatus
1CR-LSOAccuracy (Test)46.98Unverified
2Shapley-NASAccuracy (Test)46.85Unverified
3β-RDARTS-L2Accuracy (Test)46.71Unverified
4β-SDARTS-RSAccuracy (Test)46.71Unverified
5ASE-NAS+Accuracy (Val)46.66Unverified
6NARAccuracy (Test)46.66Unverified
7BaLeNAS-TFAccuracy (Test)46.54Unverified
8AG-NetAccuracy (Test)46.42Unverified
9Local searchAccuracy (Test)46.38Unverified
10NASBOTAccuracy (Test)46.37Unverified
#ModelMetricClaimedVerifiedStatus
1Balanced MixtureAccuracy (% )91.55Unverified
2GDASTop-1 Error Rate3.4Unverified
3Bonsai-NetTop-1 Error Rate3.35Unverified
4Net2 (2)Top-1 Error Rate3.3Unverified
5μDARTSTop-1 Error Rate3.28Unverified
6NN-MASS- CIFAR-CTop-1 Error Rate3.18Unverified
7NN-MASS- CIFAR-ATop-1 Error Rate3Unverified
8DARTS (first order)Top-1 Error Rate3Unverified
9NASGEPTop-1 Error Rate2.82Unverified
10AlphaX-1 (cutout NASNet)Top-1 Error Rate2.82Unverified