|
| 1 | +[[ход работы]] |
1 | 2 | # other NAS |
2 | | -| Title | Year | Source | Description | |
3 | | -| :-------------------------------------------------------------------------- | ---: | :--------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------- | |
4 | | -| Neural Architecture Search with Reinforcement Learning | 2014 | [paper](https://arxiv.org/abs/1611.01578) | Поиск архитектуры сети с использованием обучения с подкреплением с основой на RNN | |
5 | | -| Handbook of Evolutionary Computation | 1997 | [paper](https://www.taylorfrancis.com/books/edit/10.1201/9780367802486/handbook-evolutionary-computation-fogel-michalewicz-thomas-baeck) | --- | |
6 | | -| SNAS: STOCHASTIC NEURAL ARCHITECTURE SEARCH | 2020 | [papeer](https://arxiv.org/pdf/1812.09926) | | |
7 | | -| Auto-Keras: An Efficient Neural Architecture Search System | 2019 | [paper](https://sci-hub.gg/10.1145/3292500.3330648) | Поиск архитектуры на основе байесовской оптимизации. | |
8 | | -| Neural Architecture Search with Bayesian Optimisation and Optimal Transport | 2018 | [paper](https://proceedings.neurips.cc/paper_files/paper/2018/file/f33ba15effa5c10e873bf3842afb46a6-Paper.pdf) | Поиск архитектуры на основе байесовской оптимизации. | |
9 | | -| Neural predictor for<br>neural architecture search | 2019 | [paper](https://arxiv.org/pdf/1912.00848) | Пример использования GNN в качестве суррогатной функции | |
| 3 | +| Title | Year | Source | Description | |
| 4 | +| :-------------------------------------------------------------------------- | ---: | :--------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------ | |
| 5 | +| Neural Architecture Search with Reinforcement Learning | 2014 | [paper](https://arxiv.org/abs/1611.01578) | Поиск архитектуры сети с использованием обучения с подкреплением с основой на RNN | |
| 6 | +| Handbook of Evolutionary Computation | 1997 | [paper](https://www.taylorfrancis.com/books/edit/10.1201/9780367802486/handbook-evolutionary-computation-fogel-michalewicz-thomas-baeck) | --- | |
| 7 | +| SNAS: STOCHASTIC NEURAL ARCHITECTURE SEARCH | 2020 | [papeer](https://arxiv.org/pdf/1812.09926) | | |
| 8 | +| Auto-Keras: An Efficient Neural Architecture Search System | 2019 | [paper](https://sci-hub.gg/10.1145/3292500.3330648) | Поиск архитектуры на основе байесовской оптимизации. | |
| 9 | +| Neural Architecture Search with Bayesian Optimisation and Optimal Transport | 2018 | [paper](https://proceedings.neurips.cc/paper_files/paper/2018/file/f33ba15effa5c10e873bf3842afb46a6-Paper.pdf) | Поиск архитектуры на основе байесовской оптимизации. | |
| 10 | +| Neural predictor for<br>neural architecture search | 2019 | [paper](https://arxiv.org/pdf/1912.00848) | Пример использования GNN в качестве суррогатной функции | |
| 11 | +| Few-shot Neural Architecture Search | 2021 | [paper](https://proceedings.mlr.press/v139/zhao21d/zhao21d.pdf) | Использование нескольких supernet чтобы избежать обучения моделей для обучения моделей для обучения суррогатной функции с нуля. | |
| 12 | +| Neural Predictor for Neural Architecture Search | 2019 | [paper](https://arxiv.org/pdf/1912.00848) | Использование GCN для предсказания perfomance модели | |
10 | 13 |
|
11 | 14 |
|
12 | 15 | # NES |
|
15 | 18 | | Neural Ensemble Search for Uncertainty Estimation and Dataset Shift | 2021 | [paper](https://proceedings.neurips.cc/paper_files/paper/2021/hash/41a6fd31aa2e75c3c6d427db3d17ea80-Abstract.html) | Представлены два метода построения ансамбля нейронных моделей в случае сдвига в данных, также есть подробный обзор статей посвященных NES | |
16 | 19 | | Neural ensemble search via Bayesian sampling | 2022 | [paper](https://proceedings.mlr.press/v180/shu22a/shu22a.pdf) | Пример современного составления ансамбля | |
17 | 20 | | One-Shot Neural Ensemble Architecture Search by Diversity-Guided<br>Search Space Shrinking | 2021 | [paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Chen_One-Shot_Neural_Ensemble_Architecture_Search_by_Diversity-Guided_Search_Space_Shrinking_CVPR_2021_paper.pdf) | Пример современного составления ансамбля | |
18 | | -| Multi-headed neural ensemble search | 2021 | [paper](https://arxiv.org/abs/2107.04369) | ансамбли лучше | |
19 | | -| Ensemble Methods as a Defense to Adversarial Perturbations Against Deep Neural Networks | 2017 | [paper](https://arxiv.org/abs/1709.03423) | ансамбли лучше | |
20 | | - |
21 | 21 |
|
22 | 22 | # ENAS |
23 | 23 | | Title | Year | Source | Description | |
|
47 | 47 | | DARTS: Differentiable Architecture Search | 2020 | [paper](https://arxiv.org/abs/1806.09055) | - | |
48 | 48 | | Brain tumor detection using CNN, AlexNet & GoogLeNet ensembling learning approaches | 2023 | [paper](https://www.researchgate.net/publication/369308467_Brain_tumor_detection_using_CNN_AlexNet_GoogLeNet_ensembling_learning_approaches) | - | |
49 | 49 | | Combining global and local surrogate models to accelerate evolutionary optimization | 2006 | [paper](https://www.researchgate.net/publication/3421747_Combining_global_and_local_surrogate_models_to_accelerate_evolutionary_optimization_IEEE_Trans_Syst_Man_Cybern_Part_C_Appl_Rev) | - | |
50 | | -| A Density-Based Algorithm for Discovering Clusters<br>in Large Spatial Databases with Noise | 1996 | [paper](https://cdn.aaai.org/KDD/1996/KDD96-037.pdf) | DBSCAN original paper | |
| 50 | +| A Density-Based Algorithm for Discovering Clusters<br>in Large Spatial Databaseswith Noise | 1996 | [paper](https://cdn.aaai.org/KDD/1996/KDD96-037.pdf) | DBSCAN original paper | |
51 | 51 | | Adam: A Method for Stochastic Optimization | 2014 | [paper](https://arxiv.org/abs/1412.6980) | Adam original paper | |
52 | 52 | | Ensemble Classification and Regression-Recent Developments, Applications and Future Directions | 2016 | [paper](https://www.researchgate.net/profile/Le-Zhang-61/publication/290476291_Ensemble_Classification_and_Regression-Recent_Developments_Applications_and_Future_Directions_Review_Article/links/5c0a1b8fa6fdcc494fdf7e43/Ensemble-Classification-and-Regression-Recent-Developments-Applications-and-Future-Directions-Review-Article.pdf) | Рассказывается о преимуществах ансамблей над одиночными моделями при различном использовании. | |
53 | 53 | | Semi-Supervised Classification with Graph Convolutional Networks | 2016 | [paper](https://arxiv.org/abs/1609.02907) | Оригинальная статья посвященная GCN | |
54 | 54 | | [Simple and scalable predictive uncertainty estimation using deep ensembles](https://proceedings.neurips.cc/paper_files/paper/2017/hash/9ef2ed4b7fd2c810847ffa5fa85bce38-Abstract.html) | 2017 | | Реализация DeepEns -- базового алгоритма составления ансамбля на основе баггинга | |
55 | 55 | | [**Facenet**: A unified embedding for face recognition and clustering](https://www.cv-foundation.org/openaccess/content_cvpr_2015/html/Schroff_FaceNet_A_Unified_2015_CVPR_paper.html) | 2015 | | В статье представлена реализация Triplet loss | |
56 | | -| Brain tumor detection using CNN, AlexNet & GoogLeNet ensembling learning approaches. | 2023 | [paper](https://openurl.ebsco.com/EPDB%3Agcd%3A8%3A34114136/detailv2?sid=ebsco%3Aplink%3Ascholar&id=ebsco%3Agcd%3A178322108&crl=c&link_origin=scholar.google.com) | Пример того, что построние арзитектуры руками сложно | |
57 | | -| Ensemble methods in machine learning. | 2000 | [paper](https://link.springer.com/chapter/10.1007/3-540-45014-9_1) | Ансамбли лучше | |
58 | | - |
59 | | - |
60 | | - |
61 | | - |
| 56 | +| NAS-Bench-101: Towards Reproducible Neural Architecture Search | 2019 | [paper](https://proceedings.mlr.press/v97/ying19a/ying19a.pdf) | Представление графа с вершинами в виде операций | |
0 commit comments