An Image Classification Algorithm Based on Hybrid Quantum Classical Convolutional Neural Network
Quantum Engineering · 14.07.2022 · 2022 · 1-9
DOI: 10.1155/2022/5701479 ↗Kurz gefasst
Fachartikel in der Zeitschrift Quantum Engineering, erschienen am 14.07.2022. Verfasst von Wei Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.
Abstract (Originalsprache)
Quantum machine learning is emerging as a strategy to solve real-world problems. As a quantum computing model, parameterized quantum circuits provide an approach for constructing quantum machine learning algorithms, which may either realize computational acceleration or achieve better algorithm performance than classical algorithms. Based on the parameterized quantum circuit, we propose a hybrid quantum-classical convolutional neural network (HQCCNN) model for image classification that comprises both quantum and classical components. The quantum convolutional layer is designed using a parameterized quantum circuit. It is used to perform linear unitary transformation on the quantum state to extract hidden information. In addition, the quantum pooling unit is used to perform pooling operations. After the evolution of the quantum system, we measure the quantum state and input the measurement results into a classical fully connected layer for further processing. We demonstrate its potential by applying HQCCNN to the MNIST dataset. Compared to a convolutional neural network in a similar architecture, the results reveal that HQCCNN has a faster training speed and higher testing set accuracy than a convolutional neural network.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong Province
Zitieren
APA
Li, W., Chu, P., Liu, G., Tian, Y., Qiu, T., & Wang, S. (2022). An Image Classification Algorithm Based on Hybrid Quantum Classical Convolutional Neural Network. Quantum Engineering, 2022, 1-9. https://doi.org/10.1155/2022/5701479
Vancouver
Li W, Chu P, Liu G, Tian Y, Qiu T, Wang S. An Image Classification Algorithm Based on Hybrid Quantum Classical Convolutional Neural Network. Quantum Engineering. 2022;2022:1-9. doi:10.1155/2022/5701479
BibTeX
@article{Li2022,
author = {Li, Wei and Chu, Peng-Cheng and Liu, Guang-Zhe and Tian, Yan-Bing and Qiu, Tian-Hui and Wang, Shu-Mei},
title = {An Image Classification Algorithm Based on Hybrid Quantum Classical Convolutional Neural Network},
journal = {Quantum Engineering},
year = {2022},
volume = {2022},
pages = {1--9},
doi = {10.1155/2022/5701479}
}
EUVIMED