EUVIMEDEUVIMED entdecken
Crossref

Randomness-Enhanced Expressivity of Quantum Neural Networks

Yadong Wu, Juan Yao, Pengfei Zhang, Xiaopeng Li

Physical Review Letters · 05.01.2024 · 132 (1)

DOI: 10.1103/physrevlett.132.010602 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physical Review Letters, online erschienen am 05.01.2024. Verfasst von Yadong Wu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics, Fudan University, Shanghai 200438, China. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Science and Technology Commission of Shanghai Municipality.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As a hybrid of artificial intelligence and quantum computing, quantum neural networks (QNNs) have gained significant attention as a promising application on near-term, noisy intermediate-scale quantum devices. Conventional QNNs are described by parametrized quantum circuits, which perform unitary operations and measurements on quantum states. In this Letter, we propose a novel approach to enhance the expressivity of QNNs by incorporating randomness into quantum circuits. Specifically, we introduce a random layer, which contains single-qubit gates sampled from a trainable ensemble pooling. The prediction of QNN is then represented by an ensemble average over a classical function of measurement outcomes. We prove that our approach can accurately approximate arbitrary target operators using Uhlmann's theorem for majorization, which enables observable learning. Our proposal is demonstrated with extensive numerical experiments, including observable learning, Rényi entropy measurement, and image recognition. We find the expressivity of QNNs is enhanced by introducing randomness for multiple learning tasks, which could have broad application in quantum machine learning.

Autor:innen und Institutionen

  • Department of Physics, Fudan University, Shanghai 200438, China.
  • State Key Laboratory of Surface Physics, Key Laboratory of Micro and Nano Photonic Structures (MOE), Institute for Nanoelectronic Devices and Quantum Computing, Fudan University, Shanghai 200438, China.
  • Shanghai Qi Zhi Institute, AI Tower, Xuhui District, Shanghai 200232, China.
  • Shenzhen Institute for Quantum Science and Engineering, Southern University of Science and Technology, Shenzhen, 518055 Guangdong, China.
  • International Quantum Academy, Shenzhen, 518048 Guangdong, China.
  • Guangdong Provincial Key Laboratory of Quantum Science and Engineering, Southern University of Science and Technology, Shenzhen, 518055 Guangdong, China.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Science and Technology Commission of Shanghai Municipality

Zitieren

APA

Wu, Y., Yao, J., Zhang, P., & Li, X. (2024). Randomness-Enhanced Expressivity of Quantum Neural Networks. Physical Review Letters, 132(1). https://doi.org/10.1103/physrevlett.132.010602

Vancouver

Wu Y, Yao J, Zhang P, Li X. Randomness-Enhanced Expressivity of Quantum Neural Networks. Physical Review Letters. 2024;132(1). doi:10.1103/physrevlett.132.010602

BibTeX
@article{Wu2024,
  author = {Wu, Yadong and Yao, Juan and Zhang, Pengfei and Li, Xiaopeng},
  title = {Randomness-Enhanced Expressivity of Quantum Neural Networks},
  journal = {Physical Review Letters},
  year = {2024},
  volume = {132},
  number = {1},
  doi = {10.1103/physrevlett.132.010602}
}
Kostenlos starten →