由交换测试和相位估计构建的量子神经网络

doi:10.3778/j.issn.1673-9418.2410058

摘要/Abstract

摘要： 针对量子计算和神经计算的融合问题，研究了一种基于交换测试和相位估计的量子神经网络模型及算法。提出了一种采用多比特控制的交换测试量子线路，在此基础上结合相位估计提出了一种量子神经元模型。该模型的输入、权重、输出均为量子比特，其中权重比特的相位为模型参数。基于量子神经元构建了量子神经网络模型，并在该模型的输出端执行测量，以获得网络的实值输出。详细设计了与网络模型相关的各种量子线路，根据量子计算理论导出了网络各层的输入输出关系，根据梯度下降算法，详细设计网络参数的调整方法。在经典计算机上，以平面点集识别和手写体数字二分类问题为仿真对象，虽然不能验证量子计算的并行性，但能验证模型的执行效果。仿真结果表明，该模型的分类能力相较于同等参数规模的经典BP神经网络有明显优势，从而揭示出基于多比特交换测试和相位估计方法构建量子神经网络模型的研究方案是有效可行的，可为量子神经网络研究提供一种新思路。

关键词: 量子线路, 交换测试, 相位估计, 量子神经元, 量子神经网络

Abstract: To address the integration of quantum computing and neural computing, this paper investigates a quantum neural network (QNN) model and its algorithm based on swap test and phase estimation. Firstly, a quantum circuit for swap tests with multi-qubit control is proposed, and a quantum neuron model is developed by combining this with phase estimation. The model uses quantum bits for inputs, weights, and outputs, where the phase of the weight qubits serves as the model parameters. Based on this quantum neuron, a QNN model is constructed, with measurements performed at the network output to obtain real-valued outputs. Various quantum circuits associated with the network model are designed in detail, and the input-output relationships for each network layer are derived according to quantum computing theory. Additionally, a method for adjusting network parameters based on the gradient descent algorithm is thoroughly developed. Finally, simulations are conducted on a classical computer using planar point set recognition and handwritten digit binary classification. Although these simulations do not verify the parallelism of quantum computing, they do validate the model??s execution effectiveness. The results show that the proposed model has a clear advantage in classification performance compared with a classical backpropagation (BP) neural network with the same parameter scale. This demonstrates that constructing QNN models based on multi-qubit swap tests and phase estimation is both effective and feasible, offering a new perspective for future research on quantum neural networks.

Key words: quantum circuits, swap test, phase estimation, quantum neuron, quantum neural network

李盼池, 刘广硕. 由交换测试和相位估计构建的量子神经网络[J]. 计算机科学与探索, 2025, 19(9): 2399-2407.

LI Panchi, LIU Guangshuo. Quantum Neural Network Based on Swap Test and Phase Estimation[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(9): 2399-2407.

参考文献

[1] FEYNMAN R P. Simulating physics with computers[J]. International Journal of Theoretical Physics, 1982, 21(6): 467-488.
[2] TOTH G, LENT C S, TOUGAW P D, et al. Quantum cellular neural networks[J]. Superlattices and Microstructures, 1996, 20(4): 473-478.
[3] CHEN L S, LI T, CHEN Y X, et al. Design and analysis of quantum machine learning: a survey[J]. Connection Science, 2024, 36(1): 2312121.
[4] NARAYANAN A, MENNEER T. Quantum artificial neural network architectures and components[J]. Information Sciences, 2000, 128(3/4): 231-255.
[5] DU Y X, HSIEH M H, LIU T L, et al. Learnability of quantum neural networks[J]. PRX Quantum, 2021, 2(4): 040337.
[6] DA SILVA A J, DE OLIVEIRA W R, LUDERMIR T B. Weightless neural network parameters and architecture selection in a quantum computer[J]. Neurocomputing, 2016, 183: 13-22.
[7] SHAO C P, LI Y, LI H B. Quantum algorithm design: techniques and applications[J]. Journal of Systems Science and Complexity, 2019, 32(1): 375-452.
[8] ZHAO J, ZHANG Y H, SHAO C P, et al. Building quantum neural networks based on a swap test[J]. Physical Review A, 2019, 100: 012334.
[9] SHAO C P. A quantum model of feed-forward neural networks with unitary learning algorithms[J]. Quantum Information Processing, 2020, 19(3): 102.
[10] NGOC V P, WIKLICKY H. Tunable quantum neural networks for Boolean functions[EB/OL]. [2024-08-18]. https://arxiv.org/abs/2003.14122.
[11] ZHOU M G, LIU Z P, YIN H L, et al. Quantum neural network for quantum neural computing[J]. Research, 2023, 6: 0134.
[12] ABEL S, CRIADO J C, SPANNOWSKY M. Completely quantum neural networks[J]. Physical Review A, 2022, 106(2): 022601.
[13] KHALIL H, ELSHAZLY O, BAIHAN A, et al. Quantum neural networks based Lyapunov stability and adaptive learning rates for identification of nonlinear systems[J]. Ain Shams Engineering Journal, 2024, 15(8): 102851.
[14] WEN J W, HUANG Z G, CAI D B, et al. Enhancing the expressivity of quantum neural networks with residual connections[J]. Communications Physics, 2024, 7: 220.
[15] CHAKRABORTY S, DAS T, SUTRADHAR S, et al. An analytical review of quantum neural network models and relevant research[C]//Proceedings of the 2020 5th International Conference on Communication and Electronics Systems. Piscataway: IEEE, 2020: 1395-1400.
[16] KWAK Y, YUN W J, JUNG S, et al. Quantum neural networks: concepts, applications, and challenges[C]//Proceedings of the 2021 12th International Conference on Ubiquitous and Future Networks. Piscataway: IEEE, 2021: 413-416.
[17] LIAO Y D, HSIEH M H, FERRIE C. Quantum optimization for training quantum neural networks[J]. Quantum Machine Intelligence, 2024, 6(1): 33.
[18] KASHIF M, AL-KUWARI S. ResQNets: a residual approach for mitigating barren plateaus in quantum neural networks[J]. EPJ Quantum Technology, 2024, 11(1): 4.
[19] BUDIUTAMA G, DAIMON S, NISHI H, et al. Channel attention for quantum convolutional neural networks[J]. Physical Review A, 2024, 110: 012447.
[20] MAHMUD J, MASHTURA R, FATTAH S A, et al. Quantum convolutional neural networks with interaction layers for classification of classical data[J]. Quantum Machine Intelligence, 2024, 6(1): 11.
[21] NIELSEN M A, CHUANG I L. Quantum computation and quantum information[M]. Cambridge: Cambridge University Press, 2010.