Papers with Code 아카이브

Neural Architecture Search

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/automl/modnas

공식 코드

Multi-objective Differentiable Neural Architecture Search

https://github.com/automl/multi-obj-baselines

공식 코드

Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization

https://github.com/automl/nas-bench-x11

공식 코드

NAS-Bench-x11 and the Power of Learning Curves

https://github.com/automl/nas_benchmarks

공식 코드

NAS-Bench-101: Towards Reproducible Neural Architecture Search

https://github.com/automl/nasbench-1shot1

공식 코드

NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search

https://github.com/automl/nasbench301

공식 코드

Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks

https://github.com/automl/nes

공식 코드

Neural Ensemble Search for Uncertainty Estimation and Dataset Shift

https://github.com/awesomelemon/encas

공식 코드

Evolutionary Neural Cascade Search across Supernetworks

https://github.com/awesomelemon/pbt-nas

공식 코드

Shrink-Perturb Improves Architecture Mixing during Population Based Training for Neural Architecture Search

https://github.com/awslabs/syne-tune

공식 코드

Model-based Asynchronous Hyperparameter and Neural Architecture Search

https://github.com/basusourya/autoequivariant_networks

공식 코드

Autoequivariant Network Search via Group Decomposition

https://github.com/beichenzbc/supernet-shifting

공식 코드

Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach

https://github.com/ben-hawks/pytorch-jet-classify

공식 코드

Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference

https://github.com/bermanmaxim/AOWS

공식 코드

AOWS: Adaptive and optimal network width search with latency constraints

https://github.com/bestfleer/RepNAS

공식 코드

RepNAS: Searching for Efficient Re-parameterizing Blocks

https://github.com/bestfleer/shiftnas

공식 코드

ShiftNAS: Improving One-shot NAS via Probability Shift

https://github.com/bhpfelix/MTLNAS

공식 코드

MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning

https://github.com/bidyutsaha/tinytnas

공식 코드

TinyTNAS: GPU-Free, Time-Bound, Hardware-Aware Neural Architecture Search for TinyML Time Series Classification

https://github.com/boschresearch/metanas

공식 코드

Meta-Learning of Neural Architectures for Few-Shot Learning

https://github.com/brdav/atrc

공식 코드

Exploring Relational Context for Multi-Task Dense Prediction

https://github.com/brdav/bmtas

공식 코드

Automated Search for Resource-Efficient Branched Multi-Task Networks

https://github.com/brian-moser/dartsrenet

공식 코드

DartsReNet: Exploring new RNN cells in ReNet architectures

https://github.com/btma48/ITNAS

공식 코드

Inter-layer Transition in Neural Architecture Search

https://github.com/bychen515/bnnas

공식 코드

BN-NAS: Neural Architecture Search with Batch Normalization

https://github.com/bychen515/glit

공식 코드

GLiT: Neural Architecture Search for Global and Local Image Transformer

https://github.com/cambridge-mlg/arch_uncert

공식 코드

Variational Depth Search in ResNets

https://github.com/cambridgeltl/autopeft

공식 코드

AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning

https://github.com/cap-lab/S3NAS

공식 코드

S3NAS: Fast NPU-aware Neural Architecture Search Methodology

https://github.com/cat-loves-donuts/ImmuNetNAS

공식 코드

ImmuNetNAS: An Immune-network approach for searching Convolutional Neural Network Architectures

https://github.com/ccc-frankfurt/DP-NAS

공식 코드

Neural Architecture Search of Deep Priors: Towards Continual Learning without Catastrophic Interference

https://github.com/cecilia-xue/hyt-nas

공식 코드

Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image Classification

https://github.com/centaurus982034/arch-graph

공식 코드

Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search

https://github.com/cgraywang/gluon-nlp-1

공식 코드

Language Models with Transformers

https://github.com/chakkritte/SalNAS

공식 코드

SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation

https://github.com/chakkritte/eeea-net

공식 코드

EEEA-Net: An Early Exit Evolutionary Neural Architecture Search

https://github.com/changlin31/BossNAS

공식 코드

BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.