ℤ2 × ℤ2 Equivariant Quantum Neural Networks: Benchmarking against Classical Neural Networks-Reference-Cited by-同舟云学术

ℤ2 × ℤ2 Equivariant Quantum Neural Networks: Benchmarking against Classical Neural Networks

Published:2024-03-13 Issue:3 Volume:13 Page:188
ISSN:2075-1680
Container-title:Axioms
language:en
Short-container-title:Axioms

Author:

Dong Zhongtian¹^ORCID,Comajoan Cara Marçal²^ORCID,Dahale Gopal Ramesh³^ORCID,Forestano Roy T.⁴^ORCID,Gleyzer Sergei⁵^ORCID,Justice Daniel⁶^ORCID,Kong Kyoungchul¹^ORCID,Magorsch Tom⁷^ORCID,Matchev Konstantin T.⁴^ORCID,Matcheva Katia⁴^ORCID,Unlu Eyup B.⁴^ORCID

Affiliation:

1. Department of Physics & Astronomy, University of Kansas, Lawrence, KS 66045, USA

2. Department of Signal Theory and Communications, Polytechnic University of Catalonia, 08034 Barcelona, Spain

3. Indian Institute of Technology Bhilai, Kutelabhata, Khapri, District-Durg, Chhattisgarh 491001, India

4. Institute for Fundamental Theory, Physics Department, University of Florida, Gainesville, FL 32611, USA

5. Department of Physics & Astronomy, University of Alabama, Tuscaloosa, AL 35487, USA

6. Software Engineering Institute, Carnegie Mellon University, 4500 Fifth Avenue, Pittsburgh, PA 15213, USA

7. Physik-Department, Technische Universität München, James-Franck-Str. 1, 85748 Garching, Germany

Abstract

This paper presents a comparative analysis of the performance of Equivariant Quantum Neural Networks (EQNNs) and Quantum Neural Networks (QNNs), juxtaposed against their classical counterparts: Equivariant Neural Networks (ENNs) and Deep Neural Networks (DNNs). We evaluate the performance of each network with three two-dimensional toy examples for a binary classification task, focusing on model complexity (measured by the number of parameters) and the size of the training dataset. Our results show that the Z2×Z2 EQNN and the QNN provide superior performance for smaller parameter sets and modest training data samples.

Funder

National Energy Research Scientific Computing Center, a DOE Office of Science User Facility supported by the Office of Science of the U.S. Department of Energy

NERSC award

U.S. Department of Energy

College of Liberal Arts and Sciences Research Fund at the University of Kansas

Publisher

MDPI AG

Link

https://www.mdpi.com/2075-1680/13/3/188/pdf

Reference52 articles.

1. Shanahan, P., Terao, K., and Whiteson, D. (2022). Snowmass 2021 Computational Frontier CompF03 Topical Group Report: Machine Learning. arXiv.

2. Feickert, M., and Nachman, B. (2021). A Living Review of Machine Learning for Particle Physics. arXiv.

3. Balcan, M.F., and Weinberger, K.Q. (2016, January 20–22). Group Equivariant Convolutional Networks. Proceedings of the 33rd International Conference on Machine Learning, New York, NY, USA.

4. Pereira, F., Burges, C., Bottou, L., and Weinberger, K. (2012, January 3–6). ImageNet Classification with Deep Convolutional Neural Networks. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA.

5. Highly accurate protein structure prediction with AlphaFold;Jumper;Nature,2021

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Quantum Vision Transformers for Quark–Gluon Classification;Axioms;2024-05-13

2. On the universality of S_n -equivariant k-body gates;New Journal of Physics;2024-05-01