轻量量子混合网络仅用4层电路实现高效图像分类
Lean classical-quantum hybrid neural network model for image classification
- 设计四层变分量子电路的轻量混合模型，降低参数依赖
- 在MNIST、FashionMNIST、CIFAR-10上分别达100%、99.02%、85.55%准确率
- 训练更快且能有效捕捉关键特征，适合资源受限场景
将量子信息算法与神经网络结合推动了多个领域的进展。然而，现有量子机器学习图像分类多依赖传统变分量子电路，性能受参数规模制约，易导致计算资源不足与耗时增加。本文提出一种轻量级经典-量子混合神经网络（LCQHNN），仅使用四层变分电路即实现高效分类，显著降低计算成本。实验表明，该模型在MNIST、FashionMNIST和CIFAR-10数据集上分别达到100%、99.02%和85.55%的分类准确率。相同参数条件下，收敛速度优于传统模型。可视化分析显示，模型能有效提取关键数据特征，并建立特征与类别间的明确关联。研究证实，量子算法增强了模型处理复杂分类问题的能力。
原文摘要 · Abstract (English)
The integration of algorithms from quantum information with neural networks has enabled unprecedented advancements in various domains. Nonetheless, the application of quantum machine learning algorithms for image classification predominantly relies on traditional architectures such as variational quantum circuits. The performance of these models is closely tied to the scale of their parameters, with the substantial demand for parameters potentially leading to limitations in computational resources and a significant increase in computation time. In this paper, we introduce a Lean Classical-Quantum Hybrid Neural Network (LCQHNN), which achieves efficient classification performance with only four layers of variational circuits, thereby substantially reducing computational costs. Our experiments demonstrate that LCQHNN achieves 100\%, 99.02\%, and 85.55\% classification accuracy on MNIST, FashionMNIST, and CIFAR-10 datasets. Under the same parameter conditions, the convergence speed of this method is also faster than that of traditional models. Furthermore, through visualization studies, it is found that the model effectively captures key data features during training and establishes a clear association between these features and their corresponding categories. This study confirms that the employment of quantum algorithms enhances the model's ability to handle complex classification problems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。