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
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/A-LinCui/DELE
공식 코드Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS "Cold-Start"
https://github.com/ARM-software/ML-zoo
공식 코드https://github.com/AberHu/TF-NAS
공식 코드https://github.com/Alibaba-MIIL/HardCoReNAS
공식 코드HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
https://github.com/Alibaba-NLP/ACE
공식 코드Automated Concatenation of Embeddings for Structured Prediction
https://github.com/Andrew-Qibin/ssdlite-pytorch
공식 코드Rethinking Bottleneck Structure for Efficient Mobile Network Design
https://github.com/ArisChristoforidis/Dynamic-Hierarchical-NAS
공식 코드A Novel Evolutionary Algorithm for Hierarchical Neural Architecture Search
https://github.com/ArkadiyD/MacroNASBenchmark
공식 코드Local Search is a Remarkably Strong Baseline for Neural Architecture Search
https://github.com/Ascend-Research/AIO-P
공식 코드AIO-P: Expanding Neural Performance Predictors Beyond Image Classification
https://github.com/Ascend-Research/GENNAPE
공식 코드GENNAPE: Towards Generalized Neural Architecture Performance Estimators
https://github.com/AutoFP/Auto-FP
공식 코드Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data
https://github.com/AutoML-4Paradigm/AutoSTR
공식 코드AutoSTR: Efficient Backbone Search for Scene Text Recognition
https://github.com/AutoML-4Paradigm/DiffMG
공식 코드DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks
https://github.com/AutoML-4Paradigm/Interstellar
공식 코드Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding
https://github.com/AutoML-Research/S2S
공식 코드Searching to Sparsify Tensor Decomposition for N-ary Relational Data
https://github.com/Baran-phys/DynamicFormer
공식 코드https://github.com/Basvanstein/LearningFromNAS
공식 코드Neural Network Design: Learning from Neural Architecture Search
https://github.com/BayesWatch/nas-without-training
공식 코드https://github.com/Chen-yu-Zheng/AutoLC
공식 코드https://github.com/Cosijopiii/CGPNAS
공식 코드https://github.com/D-X-Y/AutoDL-Projects
공식 코드One-Shot Neural Architecture Search via Self-Evaluated Template Network
https://github.com/D-X-Y/Awesome-AutoDL
공식 코드Automated Deep Learning: Neural Architecture Search Is Not the End
https://github.com/D-X-Y/NAS-Bench-201
공식 코드NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search
https://github.com/D-X-Y/NAS-Projects
공식 코드https://github.com/D0352276/Siamese-NAS
공식 코드https://github.com/DEShawResearch/PACBayesHyperOpt
공식 코드Efficient hyperparameter optimization by way of PAC-Bayes bound minimization
https://github.com/DVM000/PreVIous
공식 코드PreVIous: A Methodology for Prediction of Visual Inference Performance on IoT Devices
https://github.com/DataDistillation/ATOM
공식 코드https://github.com/DataDistillation/D2M
공식 코드Data-to-Model Distillation: Data-Efficient Learning Framework
https://github.com/DeepInMotion/AutoCP
공식 코드Lightweight Neural Architecture Search for Cerebral Palsy Detection
https://github.com/EMI-Group/RelativeNAS
공식 코드RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning
https://github.com/Edge-AI-Acceleration-Lab/RBFleX-NAS
공식 코드https://github.com/Eric-mingjie/network-slimming
공식 코드Learning Efficient Convolutional Networks through Network Slimming
https://github.com/Eric-mingjie/rethinking-network-pruning
공식 코드https://github.com/Explorermomo/AAAI2025-AutoSGNN
공식 코드AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.