期刊
2021 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC 2021)
卷 -, 期 -, 页码 2203-2210出版社
IEEE
DOI: 10.1109/CEC45853.2021.9504945
关键词
Convolutional neural network; Neural Architectures Search; Multi-Objective
类别
资金
- National Key R&D Program of China [2017YFC1601800, 2017YFC1601000]
- National Natural Science foundation of China [62073155, 61673194, 61672263]
- Key Research and Development Program of Jiangsu Province, China [BE2017630]
- Blue Project in Jiangsu Universities
- Fundamental Research Funds for the Central Universities [JUSRP221028]
An efficient and flexible CNN architecture search algorithm (EF-CNN) is proposed in this paper, which constructs a flexible search space by considering depth, width, and lightweight blocks, and introduces a multi-objective fitness correction method. Experimental results show that the CNN architecture designed by EF-CNN is highly competitive in performance while significantly reducing computational time.
As many superior convolutional neural networks (CNNs) have been proposed in recent years, CNNs have played an important role in computer vision. However, manually-designing CNN architecture is difficult since expertise is required. Therefore, several automatic search algorithms have been proposed for neural architecture search, which usually have considerable computational complexity and the search space is limited. To address these problems, an efficient and flexible CNN architecture search algorithm (EF-CNN) is proposed in this paper. In EF-CNN, a flexible architecture search space is constructed by considering the depth, width, and lightweight blocks. In order to improve the reliability of the architecture while reducing the computational time, a multi-objective fitness correction method is proposed in EF-CNN based on the divided datasets, where the accuracy and computational complexity of architecture are considered simultaneously to design CNN. The experimental results on CIFAR-10 and CIFAR-100 indicate that the performance of CNN architecture designed by EF-CNN is very competitive while the computational time is greatly reduced.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据