A Neural Architecture Search Method using Auxiliary Evaluation Metric based on ResNet Architecture
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909879079272448 |
|---|---|
| author | Wang, Shang Tang, Huanrong Ouyang, Jianquan |
| author_facet | Wang, Shang Tang, Huanrong Ouyang, Jianquan |
| contents | This paper proposes a neural architecture search space using ResNet as a framework, with search objectives including parameters for convolution, pooling, fully connected layers, and connectivity of the residual network. In addition to recognition accuracy, this paper uses the loss value on the validation set as a secondary objective for optimization. The experimental results demonstrate that the search space of this paper together with the optimisation approach can find competitive network architectures on the MNIST, Fashion-MNIST and CIFAR100 datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01313 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Neural Architecture Search Method using Auxiliary Evaluation Metric based on ResNet Architecture Wang, Shang Tang, Huanrong Ouyang, Jianquan Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning This paper proposes a neural architecture search space using ResNet as a framework, with search objectives including parameters for convolution, pooling, fully connected layers, and connectivity of the residual network. In addition to recognition accuracy, this paper uses the loss value on the validation set as a secondary objective for optimization. The experimental results demonstrate that the search space of this paper together with the optimisation approach can find competitive network architectures on the MNIST, Fashion-MNIST and CIFAR100 datasets. |
| title | A Neural Architecture Search Method using Auxiliary Evaluation Metric based on ResNet Architecture |
| topic | Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2505.01313 |