With the rapid advance of quantum machine learning, several proposals for the quantum-analogue of convolutional neural network (CNN) have emerged. In this work, we benchmark fully parameterized quantum convolutional neural networks (QCNNs) for classical data classification. In particular, we propose a quantum neural network model inspired by CNN that only uses two-qubit interactions throughout the entire algorithm. We investigate the performance of various QCNN models differentiated by structures of parameterized quantum circuits, quantum data encoding methods, classical data pre-processing methods, cost functions and optimizers on MNIST and Fashion MNIST datasets. In most instances, QCNN achieved excellent classification accuracy despite having a small number of free parameters. The QCNN models performed noticeably better than CNN models under the similar training conditions. Since the QCNN algorithm presented in this work utilizes fully parameterized and shallow-depth quantum circuits, it is suitable for Noisy Intermediate-Scale Quantum (NISQ) devices.
Bibliographical noteFunding Information:
We thank Quantum Open Source Foundation as this work was initiated under the Quantum Computing Mentorship program.
This research is supported by the National Research Foundation of Korea (Grant No. 2019R1I1A1A01050161 and 2021M3H3A1038085) and Quantum Computing Development Program (Grant No. 2019M3E4A1080227).
© 2022, The Author(s), under exclusive licence to Springer Nature Switzerland AG.
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Computational Theory and Mathematics
- Applied Mathematics
- Theoretical Computer Science