Hybrid quantum-classical convolutional neural network for phytoplankton classification

Frontiers in Marine Science

Marine Science

Ruimin Shang¹  Guoqiang Zhong¹  Shangshang Shi¹  Jiaxin Li¹  Zhimin Wang¹  Yanan Li¹  Yongjian Gu¹ 

[1] Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China;

关键词: hybrid quantum-classical neural network;    quantum convolutional neural network;    phytoplankton classification;    parameterized quantum circuit;    ansatz;   

DOI  :  10.3389/fmars.2023.1158548

 received in 2023-02-04, accepted in 2023-09-11,  发布年份 2023

来源: Frontiers

【 摘 要 】

The taxonomic composition and abundance of phytoplankton have a direct impact on marine ecosystem dynamics and global environment change. Phytoplankton classification is crucial for phytoplankton analysis, but it is challenging due to their large quantity and small size. Machine learning is the primary method for automatically performing phytoplankton image classification. As large-scale research on marine phytoplankton generates overwhelming amounts of data, more powerful computational resources are required for the success of machine learning methods. Recently, quantum machine learning has emerged as a potential solution for large-scale data processing by harnessing the exponentially computational power of quantum computers. Here, for the first time, we demonstrate the feasibility of using quantum deep neural networks for phytoplankton classification. Hybrid quantum-classical convolutional and residual neural networks are developed based on the classical architectures. These models strike a balance between the limited function of current quantum devices and the large size of phytoplankton images, making it possible to perform phytoplankton classification on near-term quantum computers. Our quantum models demonstrate superior performance compared to their classical counterparts, exhibiting faster convergence, higher classification accuracy and lower accuracy fluctuation. The present quantum models are versatile and can be applied to various tasks of image classification in the field of marine science.

【 授权许可】

Unknown   
Copyright © 2023 Shi, Wang, Shang, Li, Li, Zhong and Gu