Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Neurocomputing

A quantum neural network with built-in self-attention mechanism

Shangshang Shi, Zhimin Wang, J. X. Li, Y. N. Li, Ruimin Shang, Haiyong Zheng, Guoqiang Zhong, Yu Gu, Xin Huang

Published Jan 26, 2026• 0 citations
Publisher
DOI
10.1016/j.neucom.2026.132862

Related papers

A Quantum Neural Network with Built-In Self-Attention Mechanism

Shangshang Shi, Zhimin Wang, Jiaxin Li +6 more

•Jan 1, 2025•0 citations

Structured Quantum Neural Networks Inspired by Multi-Head Attention Mechanisms

Chufan Lyu

International Conference on Electronic Information Engineering and Computer Technology (EIECT)•Oct 24, 2025•0 citations

Quantum self-attention neural networks for text classification

Guangxi Li, Xuanqiang Zhao, Xin Wang

arXiv:2205.05625•Science China Information Sciences•Mar 27, 2024•98 citations

A Novel Neural Network Based on Quantum Computing

Bu-Qing Chen, Xu-Feng Niu

International Journal of Theoretical Physics•May 13, 2020•15 citations

Povm-Based Quantum Self-Attention Neural Network

Jiachun Wei, Zhimin He, Chuangtao Chen +2 more

Quantum Self-Attention Neural Network (QSANN) has demonstrated remarkable potential. However, it is limited to measuring only partial information from qubits, thereby restricting its information extraction capability. Moreover, the measurement process requires multiple measurements for each qubit, leading to inefficiency in utilizing the feature space. To address these challenges, this paper introduces a novel approach called Positive Operator-Valued Measure based Quantum Self-Attention Neural Network (POVM-QSANN). It leverages POVM operators as observables, enabling the extraction of comprehensive QKV (Query-Key-Value) feature vectors from each qubit. This innovative mechanism significantly enhances information extraction capability and efficiently utilizes the feature space. The experimental results underscore the considerable advancements of POVM-QSANN on MC and RP datasets. Particularly noteworthy is its remarkable accuracy increase of 9.68% compared to QSANN on the RP dataset.

International Conference on Wavelet Analysis and Pattern Recognition•Jul 9, 2023•6 citations

A quantum-implementable neural network model

Jialin Chen, Lingli Wang, Edoardo Charbon A

Quantum Information Processing•Aug 24, 2017•27 citations
Quantum Self-Attention Neural Network (QSANN) has demonstrated remarkable potential. However, it is limited to measuring only partial information from qubits, thereby restricting its information extraction capability. Moreover, the measurement process requires multiple measurements for each qubit, leading to inefficiency in utilizing the feature space. To address these challenges, this paper introduces a novel approach called Positive Operator-Valued Measure based Quantum Self-Attention Neural Network (POVM-QSANN). It leverages POVM operators as observables, enabling the extraction of comprehensive QKV (Query-Key-Value) feature vectors from each qubit. This innovative mechanism significantly enhances information extraction capability and efficiently utilizes the feature space. The experimental results underscore the considerable advancements of POVM-QSANN on MC and RP datasets. Particularly noteworthy is its remarkable accuracy increase of 9.68% compared to QSANN on the RP dataset.