Efficient quantum feature extraction for CNN-based learning

DOI10.1016/J.JFRANKLIN.2023.06.003MaRDI QIDQ6113922zbMATH OpenFDO

Authors Tong Dou, Guofeng Zhang, Wei Cui

Publication date 11 July 2023

Published in Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2201.01246

Mathematics Subject Classification ID

Computer science (68-XX) Quantum theory (81-XX)

Abstract: Recent work has begun to explore the potential of parametrized quantum circuits (PQCs) as general function approximators. In this work, we propose a quantum-classical deep network structure to enhance classical CNN model discriminability. The convolutional layer uses linear filters to scan the input data. Moreover, we build PQC, which is a more potent function approximator, with more complex structures to capture the features within the receptive field. The feature maps are obtained by sliding the PQCs over the input in a similar way as CNN. We also give a training algorithm for the proposed model. The hybrid models used in our design are validated by numerical simulation. We demonstrate the reasonable classification performances on MNIST and we compare the performances with models in different settings. The results disclose that the model with ansatz in high expressibility achieves lower cost and higher accuracy.

Recommendations

• Quantum average neighborhood margin maximization for feature extraction
• Continuous-variable deep quantum neural networks for flexible learning of structured classical information
• Neural networks with quantum architecture and quantum learning
• Quantum speed-up for unsupervised learning
• A hybrid quantum-classical neural network with deep residual learning
• Quantum enhanced cross-validation for near-optimal neural networks architecture selection
• scientific article; zbMATH DE number 1691472
• Quantum speedup for pool-based active learning

Cites work

• Efficient depth selection for the implementation of noisy quantum approximate optimization algorithm
• From the quantum approximate optimization algorithm to a quantum alternating operator ansatz
• scientific article; zbMATH DE number 5899272 (Why is no real title available?)
• On the universality of the quantum approximate optimization algorithm
• Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer
• The quest for a quantum neural network
• The theory of variational hybrid quantum-classical algorithms

Cited in

(3)

• Quantum-enhanced feature selection with forward selection and backward elimination
• scientific article; zbMATH DE number 5669860 (Why is no real title available?)
• An algorithm based on quantum phase estimation for the identification of patterns

This page was built for publication: Efficient quantum feature extraction for CNN-based learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6113922)