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/alibaba/lightweight-neural-architecture-search
공식 코드Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition
https://github.com/allenai/dnw
공식 코드https://github.com/amazon-science/co-with-gnns-example
공식 코드Combinatorial Optimization with Automated Graph Neural Networks
https://github.com/amourwaltz/bayeslms
공식 코드Bayesian Neural Network Language Modeling for Speech Recognition
https://github.com/andreamattiagaravagno/colabnas
공식 코드Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razor
https://github.com/angusdujw/ftd-distillation
공식 코드Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation
https://github.com/ankilab/spoken-100
공식 코드https://github.com/anonxyz123/fgk62af5
공식 코드https://github.com/antaegun20/CycleGANAS
공식 코드CycleGANAS: Differentiable Neural Architecture Search for CycleGAN
https://github.com/antoyang/NAS-Benchmark
공식 코드https://github.com/aoiang/few-shot-NAS
공식 코드https://github.com/aoiang/lamoo
공식 코드https://github.com/apourchot/to_share_or_not_to_share
공식 코드To Share or Not To Share: A Comprehensive Appraisal of Weight-Sharing
https://github.com/archiiii/rram_nas_comp_pack
공식 코드RNC: Efficient RRAM-aware NAS and Compilation for DNNs on Resource-Constrained Edge Devices
https://github.com/arturjordao/StageWiseArchitectureSearch
공식 코드https://github.com/ascend-research/autobuild
공식 코드Building Optimal Neural Architectures using Interpretable Knowledge
https://github.com/ascend-research/blockprofile
공식 코드Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search
https://github.com/ashaw596/meta_architecture_search
공식 코드https://github.com/attilanagy234/enas-pytorch
공식 코드Improving the sample-efficiency of neural architecture search with reinforcement learning
https://github.com/auroua/NPENASv1
공식 코드NPENAS: Neural Predictor Guided Evolution for Neural Architecture Search
https://github.com/auroua/SSNENAS
공식 코드Self-supervised Representation Learning for Evolutionary Neural Architecture Search
https://github.com/automl-research/autograph-kddcup2020
공식 코드https://github.com/automl-research/f2gnn
공식 코드Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective
https://github.com/automl-research/pas
공식 코드https://github.com/automl-research/pas-ogb
공식 코드https://github.com/automl/Auto-PyTorch
공식 코드Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL
https://github.com/automl/BOAH
공식 코드BOAH: A Tool Suite for Multi-Fidelity Bayesian Optimization & Analysis of Hyperparameters
https://github.com/automl/DE-NAS
공식 코드https://github.com/automl/DEHB
공식 코드DEHB: Evolutionary Hyperband for Scalable, Robust and Efficient Hyperparameter Optimization
https://github.com/automl/LCBench
공식 코드Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL
https://github.com/automl/NASLib
공식 코드How Powerful are Performance Predictors in Neural Architecture Search?
https://github.com/automl/SVGe
공식 코드Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
https://github.com/automl/hierarchical_nas_construction
공식 코드Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars
https://github.com/automl/hw-aware-llm-bench
공식 코드HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models
https://github.com/automl/hw-gpt-bench
공식 코드HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.