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/pku-sec-lab/mpcvit
공식 코드https://github.com/pnnl/supersam
공식 코드https://github.com/pprp/CVPR2022-NAS-competition-Track1-3th-solution
공식 코드https://github.com/privacytrustlab/soteria_private_nn_inference
공식 코드SOTERIA: In Search of Efficient Neural Networks for Private Inference
https://github.com/pym1024/swap
공식 코드SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAS
https://github.com/qianjiangcn/eh-dnas
공식 코드EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture Search
https://github.com/quark0/darts
공식 코드https://github.com/ra225/mo-trans
공식 코드https://github.com/ra225/w-pca
공식 코드W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language Models
https://github.com/ramakanth-pasunuru/CAS-MAS
공식 코드https://github.com/raoxuan-1998/cr-lso
공식 코드https://github.com/ravikucb/dnas
공식 코드Differentiable NAS Framework and Application to Ads CTR Prediction
https://github.com/realityengines/local_search
공식 코드https://github.com/reihergroup/near
공식 코드NEAR: A Training-Free Pre-Estimator of Machine Learning Model Performance
https://github.com/reinn-cs/rnn-nas
공식 코드Multi-Objective Evolutionary Neural Architecture Search for Recurrent Neural Networks
https://github.com/ren-research/codesign
공식 코드A Semi-Decoupled Approach to Fast and Optimal Hardware-Software Co-Design of Neural Accelerators
https://github.com/rendchevi/nix-tts
공식 코드Nix-TTS: Lightweight and End-to-End Text-to-Speech via Module-wise Distillation
https://github.com/renqianluo/GBDT-NAS
공식 코드Accuracy Prediction with Non-neural Model for Neural Architecture Search
https://github.com/renqianluo/NAO
공식 코드https://github.com/renqianluo/NAO_pytorch
공식 코드https://github.com/renqianluo/SemiNAS
공식 코드https://github.com/researchmm/CDARTS
공식 코드https://github.com/researchmm/LightTrack
공식 코드LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
https://github.com/researchmm/NEAS
공식 코드One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking
https://github.com/rheasukthanker/spdnetnas
공식 코드https://github.com/rhiever/tpot
공식 코드Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science
https://github.com/rice-eic/nasa
공식 코드NASA: Neural Architecture Search and Acceleration for Hardware Inspired Hybrid Networks
https://github.com/rice-eic/supertickets
공식 코드https://github.com/rohanasthana/dinas
공식 코드Multi-conditioned Graph Diffusion for Neural Architecture Search
https://github.com/rtu715/nas-bench-360
공식 코드NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks
https://github.com/rubinxin/TSE
공식 코드Speedy Performance Estimation for Neural Architecture Search
https://github.com/ruizhong961230/embgo
공식 코드Efficient Multiplayer Battle Game Optimizer for Adversarial Robust Neural Architecture Search
https://github.com/ruizhong961230/llmo
공식 코드Large Language Model Assisted Adversarial Robustness Neural Architecture Search
https://github.com/ruocwang/darts-pt
공식 코드https://github.com/sacmehta/EdgeNets
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.