https://github.com/changlin31/DNA
공식 코드Blockwisely Supervised Neural Architecture Search with Knowledge Distillation
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/chaoji90/lhd
공식 코드https://github.com/chaoyanghe/FedNAS
공식 코드https://github.com/chaoyanghe/MiLeNAS
공식 코드MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation
https://github.com/chappers/TreeGrad
공식 코드https://github.com/chengaopro/AdversarialNAS
공식 코드AdversarialNAS: Adversarial Neural Architecture Search for GANs
https://github.com/chenwydj/architecture_convergence
공식 코드Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
https://github.com/chenxi116/PNASNet.TF
공식 코드https://github.com/chenxi116/PNASNet.pytorch
공식 코드https://github.com/chenxin061/pdarts
공식 코드Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
https://github.com/chenyaofo/CTNAS
공식 코드Contrastive Neural Architecture Search with Neural Architecture Comparators
https://github.com/chomd90/conas_release
공식 코드https://github.com/cliffbb/geppy_nn
공식 코드Evolutionary NAS with Gene Expression Programming of Cellular Encoding
https://github.com/cliffbb/uda-nas
공식 코드Unsupervised Domain Adaptation Architecture Search with Self-Training for Land Cover Mapping
https://github.com/clovaai/genas
공식 코드GeNAS: Neural Architecture Search with Better Generalization
https://github.com/cmu-catalyst/gradsign
공식 코드GradSign: Model Performance Inference with Theoretical Insights
https://github.com/cog-imperial/tree_kernel_gp
공식 코드Tree ensemble kernels for Bayesian optimization with known constraints over mixed-feature spaces
https://github.com/cognizant-ai-labs/autoinit
공식 코드AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks
https://github.com/cognizant-ai-labs/sepx-paper
공식 코드https://github.com/cogsys-tuebingen/uninas
공식 코드https://github.com/cold-rivers/LLM4HGNAS
공식 코드https://github.com/cownowan/dass
공식 코드Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets
https://github.com/cownowan/diffusionnag
공식 코드DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
https://github.com/cscvlab/VoxelReconstruction-NAS
공식 코드An Efficient End-to-End 3D Voxel Reconstruction based on Neural Architecture Search
https://github.com/dagrawa2/gsnn_classification_code
공식 코드https://github.com/dan-lb/quantum_kernel_discovery_ad_hep
공식 코드https://github.com/daniel03c1/nas_vad
공식 코드NAS-VAD: Neural Architecture Search for Voice Activity Detection
https://github.com/dapeter/nas-for-kws
공식 코드Resource-efficient DNNs for Keyword Spotting using Neural Architecture Search and Quantization
https://github.com/datadistillation/datadam
공식 코드DataDAM: Efficient Dataset Distillation with Attention Matching
https://github.com/dawnhh/dlsr-pytorch
공식 코드Differentiable Neural Architecture Search for Extremely Lightweight Image Super-Resolution
https://github.com/ddnas/ddnas
공식 코드DDNAS: Discretized Differentiable Neural Architecture Search for Text Classification
https://github.com/deepinmotion/autogcn
공식 코드AutoGCN -- Towards Generic Human Activity Recognition with Neural Architecture Search
https://github.com/devilyangs/emo-nas-cd
공식 코드https://github.com/devilyangs/enas-kt
공식 코드Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing
https://github.com/devilyangs/mfenas
공식 코드Accelerating Evolutionary Neural Architecture Search via Multi-Fidelity Evaluation
https://github.com/dichao-liu/lightweight_distracted_driver_recognition_with_distillation-based_nas_and_knowledge_transfer
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.