Scalable quantum neural networks by few quantum resources

被引：1

作者：

Pastorello, Davide ^{[1
,3
]}

Blanzieri, Enrico ^{[2
,3
]}

机构：

[1] Alma Mater Studiorum Univ Bologna, Dept Math, Piazza Porta San Donato 5, I-40126 Bologna, Italy

[2] Univ Trento, Dept Informat Engn & Comp Sci, Via Sommar 9, I-38123 Povo, Trento, Italy

[3] Trento Inst Fundamental Phys & Applicat, Via Sommar 14, I-38123 Povo, Trento, Italy

来源：

INTERNATIONAL JOURNAL OF QUANTUM INFORMATION | 2024年 / 22卷 / 07期

关键词：

Neural networks; quantum machine learning; scalable quantum computing;

D O I：

10.1142/S0219749924500187

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

This paper focuses on the construction of a general parametric model that can be implemented executing multiple swap tests over few qubits and applying a suitable measurement protocol. The model turns out to be equivalent to a two-layer feedforward neural network which can be realized combining small quantum modules. The advantages and the perspectives of the proposed quantum method are discussed.

引用

页数：16

共 18 条

[1]

Wittek P., Quantum Machine Learning, (2014)

[2]

Schuld M., Petruccione F., Machine Learning with Quantum Computers, (2021)

[3]

Pastorello D., Concise Guide to Quantum Machine Learning, (2023)

[4]

Buhrman H., Cleve R., Watrous J., de Wolf R., Phys. Rev. Lett, 87, (2001)

[5]

Fiorentino M., Kim T., Wong F. N. C., Phys. Rev. A, 72, (2005)

[6]

Kang M. S., Et al., Sci. Rep, 9, (2019)

[7]

Zhao J., Zhang Y.-H., Shao C.-P., Wu Y.-C., Guo G.-C., Guo G.-P., Phys. Rev. A, 100, (2019)

[8]

Li P., Wang B., Neural Netw, 130, (2020)

[9]

Hornik K., Stinchcombe M., White H., Neural Netw, 2, 5, (1989)

[10]

Livni R., Shalev-Shwartz S., Shamir O., On the computational efficiency of training neural networks, NIPS’14: Proc. 27th Int. Conf. Neural Information Processing Systems, pp. 855-863, (2014)

← 1 2 →