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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–10 of 1915 papers

Title	Date	Tasks	Status	Hype
DASViT: Differentiable Architecture Search for Vision Transformer	Jul 17, 2025	Evolutionary AlgorithmsNeural Architecture Search	—Unverified	0
AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory Computing	Jun 23, 2025	Neural Architecture SearchQuantization	CodeCode Available	2
From Tiny Machine Learning to Tiny Deep Learning: A Survey	Jun 21, 2025	AutoMLModel Optimization	CodeCode Available	2
DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification	Jun 17, 2025	image-classificationImage Classification	—Unverified	0
One-Shot Neural Architecture Search with Network Similarity Directed Initialization for Pathological Image Classification	Jun 17, 2025	Domain AdaptationEdge-computing	—Unverified	0
Finding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach	Jun 16, 2025	Computational Efficiencyimage-classification	—Unverified	0
MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering	Jun 16, 2025	Conformal PredictionHardware Aware Neural Architecture Search	—Unverified	0
Directed Acyclic Graph Convolutional Networks	Jun 13, 2025	Causal InferenceComputational Efficiency	—Unverified	0
Efficient Traffic Classification using HW-NAS: Advanced Analysis and Optimization for Cybersecurity on Resource-Constrained Devices	Jun 12, 2025	Hardware Aware Neural Architecture SearchNeural Architecture Search	—Unverified	0
Energy-Efficient Deep Learning for Traffic Classification on Microcontrollers	Jun 12, 2025	Computational EfficiencyDeep Learning	—Unverified	0

Show:10 25 50

← PrevPage 1 of 192Next →

All datasets ImageNet NAS-Bench-201, ImageNet-16-120 CIFAR-10 NAS-Bench-201, CIFAR-100 NAS-Bench-201, CIFAR-10 CIFAR-10 Image Classification CIFAR-100 NATS-Bench Topology, CIFAR-10 NATS-Bench Topology, CIFAR-100 NATS-Bench Topology, ImageNet16-120 Food-101 NAS-Bench-101

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	RE (Real et al., 2019)	Test Accuracy	94.13	—	Unverified
2	PPO (Schulman et al., 2017)	Test Accuracy	94.02	—	Unverified
3	TE-NAS (Chen et al., 2021)	Test Accuracy	93.9	—	Unverified
4	NASI (Shu et al., 2021)	Test Accuracy	93.55	—	Unverified
5	EigenNas (Zhu et al., 2022)	Test Accuracy	93.46	—	Unverified
6	FairNAS (Chu et al., 2021)	Test Accuracy	93.23	—	Unverified
7	KNAS (Xu et al., 2021)	Test Accuracy	93.05	—	Unverified
8	GreenMachine-1	Kendall's Tau	0.78	—	Unverified
9	GreenMachine-2	Kendall's Tau	0.66	—	Unverified
10	GreenMachine-3	Kendall's Tau	0.39	—	Unverified