Scalable Quantum Convolutional Neural Networks
This work addresses a bottleneck in quantum machine learning for researchers in the NISQ era, but it appears incremental as it builds upon existing QCNN frameworks.
The paper tackles the problem of insufficient feature extraction in classical quantum convolutional neural networks (QCNNs) by proposing a scalable QCNN (sQCNN) and a training algorithm called reverse fidelity training (RF-Train) to maximize its performance.
With the beginning of the noisy intermediate-scale quantum (NISQ) era, quantum neural network (QNN) has recently emerged as a solution for the problems that classical neural networks cannot solve. Moreover, QCNN is attracting attention as the next generation of QNN because it can process high-dimensional vector input. However, due to the nature of quantum computing, it is difficult for the classical QCNN to extract a sufficient number of features. Motivated by this, we propose a new version of QCNN, named scalable quantum convolutional neural network (sQCNN). In addition, using the fidelity of QC, we propose an sQCNN training algorithm named reverse fidelity training (RF-Train) that maximizes the performance of sQCNN.