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 1–10 of 1915 papers

TitleStatusHype
DASViT: Differentiable Architecture Search for Vision Transformer—0
AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory ComputingCode2
From Tiny Machine Learning to Tiny Deep Learning: A SurveyCode2
DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification—0
One-Shot Neural Architecture Search with Network Similarity Directed Initialization for Pathological Image Classification—0
Finding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach—0
MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering—0
Directed Acyclic Graph Convolutional Networks—0
Efficient Traffic Classification using HW-NAS: Advanced Analysis and Optimization for Cybersecurity on Resource-Constrained Devices—0
Energy-Efficient Deep Learning for Traffic Classification on Microcontrollers—0
Show:102550
← PrevPage 1 of 192Next →

Benchmark Results

#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