Image classification is a crucial task in machine learning. In recent years,
this field has witnessed rapid development, with a series of image
classification models being proposed and achieving state-of-the-art (SOTA)
results. Parallelly, with the advancement of quantum technologies, quantum
machine learning has attracted a lot of interest. In particular, a class of
algorithms known as variational quantum algorithms (VQAs) has been extensively
studied to improve the performance of classical machine learning. In this
paper, we propose a novel image classification framework using VQAs. The major
advantage of our framework is the elimination of the need for the global
pooling operation typically performed at the end of classical image
classification models. While global pooling can help to reduce computational
complexity, it often results in a significant loss of information. By removing
the global pooling module before the output layer, our approach allows for
effectively capturing more discriminative features and fine-grained details in
images, leading to improved classification performance. Moreover, employing
VQAs enables our framework to have fewer parameters compared to the classical
framework, even in the absence of global pooling, which makes it more
advantageous in preventing overfitting. We apply our method to different SOTA
image classification models and demonstrate the superiority of the proposed
quantum architecture over its classical counterpart through a series of
experiments on public datasets.

使用变分量子算法构建的图像分类框架在消除全局汇聚操作的需求的基础上，通过有效地捕捉图像中更有区分度的特征和细节，提高了分类性能，并且相比于经典框架具有更少的参数，更有效地防止过拟合。

基于变分量子算法的一种新框架：图像分类的革命性突破

A Novel Framework Based on Variational Quantum Algorithms:  Revolutionizing Image Classification

While quantum architectures are still under development, when available, they
will only be able to process quantum data when machine learning algorithms can
only process numerical data. Therefore, in the issues of classification or
regression, it is necessary to simulate and study quantum systems that will
transfer the numerical input data to a quantum form and enable quantum
computers to use the available methods of machine learning. This material
includes the results of experiments on training and performance of a hybrid
quantum-classical neural network developed for the problem of classification of
handwritten digits from the MNIST data set. The comparative results of two
models: classical and quantum neural networks of a similar number of training
parameters, indicate that the quantum network, although its simulation is
time-consuming, overcomes the classical network (it has better convergence and
achieves higher training and testing accuracy).

研究了用于手写数字 MNIST 数据集分类问题的混合量子 - 经典神经网络的性能，结果表明虽然模拟时间较长，但是该模型优于传统网络，达到更好的收敛性和高的训练和测试精度。

量子与经典神经网络模型在图像分类任务中的比较

Comparing concepts of quantum and classical neural network models for  image classification task

A central aspect for operating future quantum computers is quantum circuit
optimization, i.e., the search for efficient realizations of quantum algorithms
given the device capabilities. In recent years, powerful approaches have been
developed which focus on optimizing the high-level circuit structure. However,
these approaches do not consider and thus cannot optimize for the hardware
details of the quantum architecture, which is especially important for
near-term devices. To address this point, we present an approach to quantum
circuit optimization based on reinforcement learning. We demonstrate how an
agent, realized by a deep convolutional neural network, can autonomously learn
generic strategies to optimize arbitrary circuits on a specific architecture,
where the optimization target can be chosen freely by the user. We demonstrate
the feasibility of this approach by training agents on 12-qubit random
circuits, where we find on average a depth reduction by 27% and a gate count
reduction by 15%. We examine the extrapolation to larger circuits than used for
training, and envision how this approach can be utilized for near-term quantum
devices.

本研究使用基于强化学习的方法对量子电路进行优化，通过深度卷积神经网络，实现了对于特定架构的任意量子电路的自主学习及优化。对 12 比特电路进行实验得出优化效果，平均深度降低 27％，门数降低 15％，并探讨了方法在近期量子设备上的可行性。