AutoML
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 4
- 보존된 평가 기록
- 11
Automated Machine Learning (AutoML) is a general concept which covers diverse techniques for automated model learning including automatic data preprocessing, architecture search, and model selection. Source: Evaluating recommender systems for AI-driven data science (1905.09205)
Source: CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/marscod/BERT-Sort
https://github.com/maxwelltsai/DeepGalaxy
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/mayankk6196/darts-python
https://github.com/mc-nya/fednest
Optimizing Millions of Hyperparameters by Implicit Differentiation
https://github.com/megvii-model/AngleNAS
Angle-based Search Space Shrinking for Neural Architecture Search
https://github.com/megvii-model/MetaPruning
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
https://github.com/megvii-model/SinglePathOneShot
Single Path One-Shot Neural Architecture Search with Uniform Sampling
https://github.com/megvii-research/basecls/tree/main/zoo/public/effnet
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/meijieru/yet_another_mobilenet_series
MnasNet: Platform-Aware Neural Architecture Search for Mobile
https://github.com/melodyguan/enas
https://github.com/mfeurer/rgpe-code-release
https://github.com/michael-snower/ppo
https://github.com/microsoft/NeuralSpeech/tree/master/LightSpeech
LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search
https://github.com/microsoft/moonlit
SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference
https://github.com/microsoft/nn-meter
Random Search and Reproducibility for Neural Architecture Search
https://github.com/microsoft/only_train_once
https://github.com/microsoft/strategically_efficient_rl
https://github.com/microsoft/ticl
TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
https://github.com/midasklr/yolov5prune
Learning Efficient Convolutional Networks through Network Slimming
https://github.com/mightypirate1/PPO_homebrew
https://github.com/mindspore-ai/models/blob/master/research/cv/efficientnet-b0
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
https://github.com/mindspore-ai/models/blob/master/research/cv/efficientnetv2
https://github.com/mindspore-ai/models/blob/master/research/cv/mnasnet
MnasNet: Platform-Aware Neural Architecture Search for Mobile
https://github.com/mindspore-ai/models/blob/master/research/cv/mobilenetv3_large
https://github.com/mindspore-ai/models/tree/master/official/cv/nasnet
Learning Transferable Architectures for Scalable Image Recognition
https://github.com/mindspore-ai/models/tree/master/research/cv/Auto-DeepLab
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
https://github.com/mindspore-ai/models/tree/master/research/cv/EfficientDet_d0
https://github.com/mindspore-ai/models/tree/master/research/cv/HourNAS
HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens
https://github.com/mindspore-ai/models/tree/master/research/cv/PDarts
Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
https://github.com/mindspore-ai/models/tree/master/research/cv/adelaide_ea
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
https://github.com/mindspore-ai/models/tree/master/research/cv/nas-fpn
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
https://github.com/mindspore-ai/models/tree/master/research/cv/pnasnet
https://github.com/mindspore-ai/models/tree/master/research/cv/proxylessnas
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
https://github.com/mindspore-ai/models/tree/master/research/cv/renas
https://github.com/mindspore-ai/models/tree/master/research/cv/resnet50_bam
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.