Insights from the Use of Previously Unseen Neural Architecture Search Datasets
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913296662134784 |
|---|---|
| author | Geada, Rob Towers, David Forshaw, Matthew Atapour-Abarghouei, Amir McGough, A. Stephen |
| author_facet | Geada, Rob Towers, David Forshaw, Matthew Atapour-Abarghouei, Amir McGough, A. Stephen |
| contents | The boundless possibility of neural networks which can be used to solve a problem -- each with different performance -- leads to a situation where a Deep Learning expert is required to identify the best neural network. This goes against the hope of removing the need for experts. Neural Architecture Search (NAS) offers a solution to this by automatically identifying the best architecture. However, to date, NAS work has focused on a small set of datasets which we argue are not representative of real-world problems. We introduce eight new datasets created for a series of NAS Challenges: AddNIST, Language, MultNIST, CIFARTile, Gutenberg, Isabella, GeoClassing, and Chesseract. These datasets and challenges are developed to direct attention to issues in NAS development and to encourage authors to consider how their models will perform on datasets unknown to them at development time. We present experimentation using standard Deep Learning methods as well as the best results from challenge participants. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_02189 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Insights from the Use of Previously Unseen Neural Architecture Search Datasets Geada, Rob Towers, David Forshaw, Matthew Atapour-Abarghouei, Amir McGough, A. Stephen Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition The boundless possibility of neural networks which can be used to solve a problem -- each with different performance -- leads to a situation where a Deep Learning expert is required to identify the best neural network. This goes against the hope of removing the need for experts. Neural Architecture Search (NAS) offers a solution to this by automatically identifying the best architecture. However, to date, NAS work has focused on a small set of datasets which we argue are not representative of real-world problems. We introduce eight new datasets created for a series of NAS Challenges: AddNIST, Language, MultNIST, CIFARTile, Gutenberg, Isabella, GeoClassing, and Chesseract. These datasets and challenges are developed to direct attention to issues in NAS development and to encourage authors to consider how their models will perform on datasets unknown to them at development time. We present experimentation using standard Deep Learning methods as well as the best results from challenge participants. |
| title | Insights from the Use of Previously Unseen Neural Architecture Search Datasets |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.02189 |