Papers with Code 아카이브
Neural Architecture Search
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 26
- 보존된 평가 기록
- 424
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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Transferrable Surrogates in Expressive Neural Architecture Search Spaces
DASViT: Differentiable Architecture Search for Vision Transformer
AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory Computing
From Tiny Machine Learning to Tiny Deep Learning: A Survey
One-Shot Neural Architecture Search with Network Similarity Directed Initialization for Pathological Image Classification
DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification
MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering
Finding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach
Directed Acyclic Graph Convolutional Networks
Energy-Efficient Deep Learning for Traffic Classification on Microcontrollers
Efficient Traffic Classification using HW-NAS: Advanced Analysis and Optimization for Cybersecurity on Resource-Constrained Devices
SWAT-NN: Simultaneous Weights and Architecture Training for Neural Networks in a Latent Space
Flexiffusion: Training-Free Segment-Wise Neural Architecture Search for Efficient Diffusion Models
Structured Pruning and Quantization for Learned Image Compression
Global optimization of graph acquisition functions for neural architecture search
Gibbs randomness-compression proposition: An efficient deep learning
CrossNAS: A Cross-Layer Neural Architecture Search Framework for PIM Systems
Optimizing edge AI models on HPC systems with the edge in the loop
Auto-nnU-Net: Towards Automated Medical Image Segmentation
Guidelines for the Quality Assessment of Energy-Aware NAS Benchmarks
DimGrow: Memory-Efficient Field-level Embedding Dimension Search
Half Search Space is All You Need
From Hand-Crafted Metrics to Evolved Training-Free Performance Predictors for Neural Architecture Search via Genetic Programming
SEAL: Searching Expandable Architectures for Incremental Learning
MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices
GreenFactory: Ensembling Zero-Cost Proxies to Estimate Performance of Neural Networks
Differentiable Channel Selection in Self-Attention For Person Re-Identification
L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformers
NeuRN: Neuro-inspired Domain Generalization for Image Classification
A systematic review of challenges and proposed solutions in modeling multimodal data
Underwater object detection in sonar imagery with detection transformer and Zero-shot neural architecture search
Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey
Llama-Nemotron: Efficient Reasoning Models
A Neural Architecture Search Method using Auxiliary Evaluation Metric based on ResNet Architecture
A Transformer-based Neural Architecture Search Method
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.