arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.00661quant-ph
收藏

用于经典数据分类的量子卷积神经网络

Quantum convolutional neural network for classical data classification

Tak Hur, Leeseok Kim, Daniel K. Park

摘要:

随着量子机器学习的快速发展,出现了几种卷积神经网络(CNN)的量子模拟方案。在这项工作中,我们对完全参数化的量子卷积神经网络(QCNN)进行了经典数据分类的基准测试。特别是,我们提出了一个受CNN启发的量子神经网络模型,该模型在整个算法中只使用两个量子比特的相互作用。我们研究了各种QCNN模型的性能,这些模型通过参数化量子线路的结构、量子数据编码方法、经典数据预处理方法、成本函数和优化器在MNIST和Fashion MNIST数据集上进行区分。在大多数情况下,QCNN实现了出色的分类精度,尽管有少量的自由参数。在相似的训练条件下,QCNN模型的性能明显优于CNN模型。由于本文提出的QCNN算法利用了完全参数化和浅深度的量子线路,因此适用于噪声中间尺度量子(NISQ)器件。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑