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/tdenottelander/MacroNAS

공식 코드

Local Search is a Remarkably Strong Baseline for Neural Architecture Search

https://github.com/tend93/cvpr2021_nas_competition_track1_1st_solution

공식 코드

Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Training

https://github.com/tensorflow/adanet

공식 코드

Improving Neural Architecture Search Image Classifiers via Ensemble Learning

https://github.com/tensorflow/models

공식 코드

Neural Architecture Search with Reinforcement Learning

https://github.com/tensorflow/models/blob/master/official/vision/modeling/backbones/mobilenet.py

공식 코드

MobileNetV4 -- Universal Models for the Mobile Ecosystem

https://github.com/tensorflow/models/tree/master/official/vision/beta/modeling/backbones

공식 코드

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

https://github.com/tensorflow/tensor2tensor

공식 코드

The Evolved Transformer

https://github.com/tensorflow/tpu

공식 코드

MnasNet: Platform-Aware Neural Architecture Search for Mobile

https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet

공식 코드

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

https://github.com/ternencewu123/gautomri

공식 코드

Generalizable Learning Reconstruction for Accelerating MR Imaging via Federated Neural Architecture Search

https://github.com/tess100766/manas

공식 코드

Manas: Mining Software Repositories to Assist AutoML

https://github.com/themody/nasforsentenceembeddingheads

공식 코드

Neural Architecture Search for Sentence Classification with BERT

https://github.com/thomasfirmin/hpo_snn

공식 코드

Parallel Hyperparameter Optimization Of Spiking Neural Network

https://github.com/thu-spmi/ST-NAS

공식 코드

Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients

https://github.com/thumnlab/autogl-light

공식 코드

AutoGL: A Library for Automated Graph Learning

https://github.com/thumnlab/nas-bench-graph

공식 코드

NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search

https://github.com/thunderstruct/hivenas

공식 코드

HiveNAS: Neural Architecture Search using Artificial Bee Colony Optimization

https://github.com/tianyic/only_train_once

공식 코드

Automated Search-Space Generation Neural Architecture Search

https://github.com/timofeevalex/ssnas_imbalanced

공식 코드

Self-Supervised Neural Architecture Search for Imbalanced Datasets

https://github.com/tinyvision/damo-yolo

공식 코드

DAMO-YOLO : A Report on Real-Time Object Detection Design

https://github.com/tisabe/jraph_mpeu

공식 코드

Band-gap regression with architecture-optimized message-passing neural networks

https://github.com/tommiekerssies/autopatch

공식 코드

Neural Architecture Search for Visual Anomaly Segmentation

https://github.com/tomomasayamasaki/RBFleX-NAS

공식 코드

RBFleX-NAS: Training-Free Neural Architecture Search Using Radial Basis Function Kernel and Hyperparameter Detection

https://github.com/tongzhou0101/obfunas

공식 코드

ObfuNAS: A Neural Architecture Search-based DNN Obfuscation Approach

https://github.com/towers-d/nas-unseen-datasets

공식 코드

Insights from the Use of Previously Unseen Neural Architecture Search Datasets

https://github.com/tsinghua-ideal/Canvas

공식 코드

Canvas: End-to-End Kernel Architecture Search in Neural Networks

https://github.com/tsumansapkota/noisy-heuristics-nas

공식 코드

Noisy Heuristics NAS: A Network Morphism based Neural Architecture Search using Heuristics

https://github.com/ubc-nlp/llmas

공식 코드

LLM Performance Predictors are good initializers for Architecture Search

https://github.com/ubc-nlp/mos

공식 코드

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts

https://github.com/ultmaster/acenas

공식 코드

Learning to Rank Ace Neural Architectures via Normalized Discounted Cumulative Gain

https://github.com/ultmaster/deeper-insights-weight-sharing

공식 코드

Deeper Insights into Weight Sharing in Neural Architecture Search

https://github.com/umair-nasir14/llmatic

공식 코드

LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization

https://github.com/utkarshnath/Adjoint-Network

공식 코드

Adjoined Networks: A Training Paradigm with Applications to Network Compression

https://github.com/vascolopes/lcmnas

공식 코드

Towards Less Constrained Macro-Neural Architecture Search

https://github.com/vascolopes/nas-benchmark-evaluation

공식 코드

Are Neural Architecture Search Benchmarks Well Designed? A Deeper Look Into Operation Importance

https://github.com/vdigpku/flownas

공식 코드

FlowNAS: Neural Architecture Search for Optical Flow Estimation

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