.png){kind=icon}
返回
Evolving convolutional autoencoders using multi-objective Particle Swarm Optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compeleceng.2021.107108.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Convolution autoencoders have shown that they have useful applications in multiple areas related to image classification and generation. The architecture of deep neural networks has a huge impact on the performance of the network. In recent years, metaheuristics have become quite popular for the optimization of the architectures of deep neural networks. In this paper, we propose a multi-objective Particle Swarm Optimization (PSO) for designing flexible convolution autoencoders by evolving the arrangement of convolution and pooling layers along with the number of parameters. A novel encoding strategy for PSO particles is introduced, which allows flexible positioning of pooling layers. To enhance the exploration of the search space, velocity and the position update methods for variable-length particles in PSO are also modified. The proposed method is evaluated on different datasets for image classification. The experimental results show that the resultant architectures are more generalized, optimized, and accurate than their competitors.
Keyword:
Deep architecture optimization
Evolutionary deep learning
Image Classification
Multi-objective Particle Swarm Optimization (MOPSO)
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
C
IF:
4.9
论文数:
6.7K
被引数:
1.3W
机构
暂无机构信息
引用论文
.png){kind=icon}
分享收藏分享收藏分享收藏
查看更多内容