Quantum convolutional neural network for classical data classification

Tak Hur

doi:10.1007/s42484-021-00061-x

Quantum convolutional neural network for classical data classification

2022-02-10

125

OA

AI

DOI：10.1007/s42484-021-00061-x

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Quantum machine learning

Convolutional neural network

Deep learning

Quantum convolutional neural network for classical data classification

Abstract

Journal

Organization