4.5 Article

Image classification and adversarial robustness analysis based on hybrid convolutional neural network

期刊

OPTICS COMMUNICATIONS
卷 533, 期 -, 页码 -

出版社

ELSEVIER
DOI: 10.1016/j.optcom.2023.129287

关键词

Convolutional neural network; Quantum convolutional neural network; Adversarial robustness; Image classification

类别

向作者/读者索取更多资源

Hybrid quantum and classical classification algorithms have provided a new solution to the classification problem, by designing quantum convolutional filters to enhance feature extraction ability and creating a hybrid quantum-classical convolutional neural network model. The feasibility of the proposed hybrid model is tested on the classical MNIST dataset, and it is demonstrated that the hybrid model outperforms the original convolutional neural network and the quanvolutional neural network in some adversarial cases.
ABS T R A C T Hybrid quantum and classical classification algorithms have provided a new solution to the classification problem with machine learning methods under a hybrid computing environment. Enlightened by the potential powerful quantum computing and the benefits of convolutional neural network, a quantum analog of the convolutional kernel of the classical convolutional neural network, i.e., quantum convolutional filter, is designed to enhance the feature extraction ability. Meanwhile, quantum convolutional layers stacked by quantum convolutional filters combine variational quantum circuits with tensor network architecture and convolution operations. In addition, a hybrid quantum-classical convolutional neural network model containing quantum convolution layers and classical networks is devised. The feasibility of the proposed hybrid model are tested on the classical MNIST dataset. Finally, the adversarial robustness of the presented hybrid network is compared with that of the classical convolutional neural network and the quanvolutional one under classical adversarial examples. It is demonstrated the presented hybrid quantum-classical convolutional neural network model outperforms the original convolutional neural network and the quanvolutional neural network in some adversarial cases.

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。

评论

主要评分

4.5
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据