Image recognition and classification are fundamental tasks with diverse
practical applications across various industries, making them critical in the
modern world. Recently, machine learning models, particularly neural networks,
have emerged as powerful tools for solving these problems. However, the
utilization of quantum effects through hybrid quantum-classical approaches can
further enhance the capabilities of traditional classical models. Here, we
propose two hybrid quantum-classical models: a neural network with parallel
quantum layers and a neural network with a quanvolutional layer, which address
image classification problems. One of our hybrid quantum approaches
demonstrates remarkable accuracy of more than 99% on the MNIST dataset.
Notably, in the proposed quantum circuits all variational parameters are
trainable, and we divide the quantum part into multiple parallel variational
quantum circuits for efficient neural network learning. In summary, our study
contributes to the ongoing research on improving image recognition and
classification using quantum machine learning techniques. Our results provide
promising evidence for the potential of hybrid quantum-classical models to
further advance these tasks in various fields, including healthcare, security,
and marketing.

本研究提出了两种混合量子 - 经典模型：具有平行量子层的神经网络和具有量子卷积层的神经网络，它们解决了图像分类问题。其中我们提出的混合量子方法在 MNIST 数据集上展现了超过 99% 的准确率。这表明将量子效应应用于传统经典模型可以进一步提高图像识别和分类的能力，并为医疗保健、安全和市场营销等各个领域提供有前途的方法。