Quantifying the effects of noise in a quantum convolutional neural network, by Zeyu Fan, Jonathan Wei Zhong Lau, Leong-Chuan Kwek
Summarize this article with:
SciPost Physics Core Home Authoring Refereeing Submit a manuscript About Quantifying the effects of noise in a quantum convolutional neural network Zeyu Fan, Jonathan Wei Zhong Lau, Leong-Chuan Kwek SciPost Phys. Core 8, 093 (2025) · published 18 December 2025 doi: 10.21468/SciPostPhysCore.8.4.093 pdf BiBTeX RIS Submissions/Reports Abstract This study quantifies the effects of quantum noise on the performance of a quantum convolutional neural network (QCNN), building on parallels with classical convolutional neural networks (CNNs), where added Gaussian noise can improve training speed, accuracy, and generalizability. While such benefits are established for classical CNNs, the influence of noise on quantum counterparts remains insufficiently characterized. We specifically examine three types of quantum noise: decoherence, Gaussian noise arising from imperfect quantum gates and experimental error, and systematic noise introduced during input state preparation. Our analysis provides a detailed assessment of how these distinct noise sources affect QCNN operation and outlines considerations for mitigating their impact. Though a QCNN is used as an example in this work, the methods used here can be applied to other quantum machine learning models as well. × TY - JOURPB - SciPost FoundationDO - 10.21468/SciPostPhysCore.8.4.093TI - Quantifying the effects of noise in a quantum convolutional neural networkPY - 2025/12/18UR - https://scipost.org/SciPostPhysCore.8.4.093JF - SciPost Physics CoreJA - SciPost Phys. CoreVL - 8IS - 4SP - 093A1 - Fan, ZeyuAU - Lau, Jonathan Wei ZhongAU - Kwek, Leong-ChuanAB - This study quantifies the effects of quantum noise on the performance of a quantum convolutional neural network (QCNN), building on parallels with classical convolutional neural networks (CNNs), where added Gaussian noise can improve training speed, accuracy, and generalizability. While such benefits are established for classical CNNs, the influence of noise on quantum counterparts remains insufficiently characterized. We specifically examine three types of quantum noise: decoherence, Gaussian noise arising from imperfect quantum gates and experimental error, and systematic noise introduced during input state preparation. Our analysis provides a detailed assessment of how these distinct noise sources affect QCNN operation and outlines considerations for mitigating their impact. Though a QCNN is used as an example in this work, the methods used here can be applied to other quantum machine learning models as well.ER - × @Article{10.21468/SciPostPhysCore.8.4.093, title={{Quantifying the effects of noise in a quantum convolutional neural network}}, author={Zeyu Fan and Jonathan Wei Zhong Lau and Leong-Chuan Kwek}, journal={SciPost Phys. Core}, volume={8}, pages={093}, year={2025}, publisher={SciPost}, doi={10.21468/SciPostPhysCore.8.4.093}, url={https://scipost.org/10.21468/SciPostPhysCore.8.4.093},} Authors / Affiliations: mappings to Contributors and Organizations See all Organizations. 1 Zeyu Fan, 1 Jonathan Wei Zhong Lau, 1 2 3 Leong-Chuan Kwek 1 National University of Singapore [NUS] 2 Universiti Teknologi Nanyang / Nanyang Technological University [NTU] 3 UMI MajuLab Funders for the research work leading to this publication Ministry of Education - Singapore National Research Foundation Singapore (NRF) (through Organization: National Research Foundation - Singapore [NRF])