Cargando…

A Multi-Classification Hybrid Quantum Neural Network Using an All-Qubit Multi-Observable Measurement Strategy

Quantum machine learning is a promising application of quantum computing for data classification. However, most of the previous research focused on binary classification, and there are few studies on multi-classification. The major challenge comes from the limitations of near-term quantum devices on...

Descripción completa

Detalles Bibliográficos
Autores principales: Zeng, Yi, Wang, Hao, He, Jin, Huang, Qijun, Chang, Sheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947049/
https://www.ncbi.nlm.nih.gov/pubmed/35327905
http://dx.doi.org/10.3390/e24030394
_version_ 1784674346291167232
author Zeng, Yi
Wang, Hao
He, Jin
Huang, Qijun
Chang, Sheng
author_facet Zeng, Yi
Wang, Hao
He, Jin
Huang, Qijun
Chang, Sheng
author_sort Zeng, Yi
collection PubMed
description Quantum machine learning is a promising application of quantum computing for data classification. However, most of the previous research focused on binary classification, and there are few studies on multi-classification. The major challenge comes from the limitations of near-term quantum devices on the number of qubits and the size of quantum circuits. In this paper, we propose a hybrid quantum neural network to implement multi-classification of a real-world dataset. We use an average pooling downsampling strategy to reduce the dimensionality of samples, and we design a ladder-like parameterized quantum circuit to disentangle the input states. Besides this, we adopt an all-qubit multi-observable measurement strategy to capture sufficient hidden information from the quantum system. The experimental results show that our algorithm outperforms the classical neural network and performs especially well on different multi-class datasets, which provides some enlightenment for the application of quantum computing to real-world data on near-term quantum processors.
format Online
Article
Text
id pubmed-8947049
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-89470492022-03-25 A Multi-Classification Hybrid Quantum Neural Network Using an All-Qubit Multi-Observable Measurement Strategy Zeng, Yi Wang, Hao He, Jin Huang, Qijun Chang, Sheng Entropy (Basel) Article Quantum machine learning is a promising application of quantum computing for data classification. However, most of the previous research focused on binary classification, and there are few studies on multi-classification. The major challenge comes from the limitations of near-term quantum devices on the number of qubits and the size of quantum circuits. In this paper, we propose a hybrid quantum neural network to implement multi-classification of a real-world dataset. We use an average pooling downsampling strategy to reduce the dimensionality of samples, and we design a ladder-like parameterized quantum circuit to disentangle the input states. Besides this, we adopt an all-qubit multi-observable measurement strategy to capture sufficient hidden information from the quantum system. The experimental results show that our algorithm outperforms the classical neural network and performs especially well on different multi-class datasets, which provides some enlightenment for the application of quantum computing to real-world data on near-term quantum processors. MDPI 2022-03-11 /pmc/articles/PMC8947049/ /pubmed/35327905 http://dx.doi.org/10.3390/e24030394 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zeng, Yi
Wang, Hao
He, Jin
Huang, Qijun
Chang, Sheng
A Multi-Classification Hybrid Quantum Neural Network Using an All-Qubit Multi-Observable Measurement Strategy
title A Multi-Classification Hybrid Quantum Neural Network Using an All-Qubit Multi-Observable Measurement Strategy
title_full A Multi-Classification Hybrid Quantum Neural Network Using an All-Qubit Multi-Observable Measurement Strategy
title_fullStr A Multi-Classification Hybrid Quantum Neural Network Using an All-Qubit Multi-Observable Measurement Strategy
title_full_unstemmed A Multi-Classification Hybrid Quantum Neural Network Using an All-Qubit Multi-Observable Measurement Strategy
title_short A Multi-Classification Hybrid Quantum Neural Network Using an All-Qubit Multi-Observable Measurement Strategy
title_sort multi-classification hybrid quantum neural network using an all-qubit multi-observable measurement strategy
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947049/
https://www.ncbi.nlm.nih.gov/pubmed/35327905
http://dx.doi.org/10.3390/e24030394
work_keys_str_mv AT zengyi amulticlassificationhybridquantumneuralnetworkusinganallqubitmultiobservablemeasurementstrategy
AT wanghao amulticlassificationhybridquantumneuralnetworkusinganallqubitmultiobservablemeasurementstrategy
AT hejin amulticlassificationhybridquantumneuralnetworkusinganallqubitmultiobservablemeasurementstrategy
AT huangqijun amulticlassificationhybridquantumneuralnetworkusinganallqubitmultiobservablemeasurementstrategy
AT changsheng amulticlassificationhybridquantumneuralnetworkusinganallqubitmultiobservablemeasurementstrategy
AT zengyi multiclassificationhybridquantumneuralnetworkusinganallqubitmultiobservablemeasurementstrategy
AT wanghao multiclassificationhybridquantumneuralnetworkusinganallqubitmultiobservablemeasurementstrategy
AT hejin multiclassificationhybridquantumneuralnetworkusinganallqubitmultiobservablemeasurementstrategy
AT huangqijun multiclassificationhybridquantumneuralnetworkusinganallqubitmultiobservablemeasurementstrategy
AT changsheng multiclassificationhybridquantumneuralnetworkusinganallqubitmultiobservablemeasurementstrategy