Cargando…

Accurate Image Multi-Class Classification Neural Network Model with Quantum Entanglement Approach

Quantum machine learning (QML) has attracted significant research attention over the last decade. Multiple models have been developed to demonstrate the practical applications of the quantum properties. In this study, we first demonstrate that the previously proposed quanvolutional neural network (Q...

Descripción completa

Detalles Bibliográficos
Autores principales: Riaz, Farina, Abdulla, Shahab, Suzuki, Hajime, Ganguly, Srinjoy, Deo, Ravinesh C., Hopkins, Susan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007163/
https://www.ncbi.nlm.nih.gov/pubmed/36904951
http://dx.doi.org/10.3390/s23052753
_version_ 1784905450722951168
author Riaz, Farina
Abdulla, Shahab
Suzuki, Hajime
Ganguly, Srinjoy
Deo, Ravinesh C.
Hopkins, Susan
author_facet Riaz, Farina
Abdulla, Shahab
Suzuki, Hajime
Ganguly, Srinjoy
Deo, Ravinesh C.
Hopkins, Susan
author_sort Riaz, Farina
collection PubMed
description Quantum machine learning (QML) has attracted significant research attention over the last decade. Multiple models have been developed to demonstrate the practical applications of the quantum properties. In this study, we first demonstrate that the previously proposed quanvolutional neural network (QuanvNN) using a randomly generated quantum circuit improves the image classification accuracy of a fully connected neural network against the Modified National Institute of Standards and Technology (MNIST) dataset and the Canadian Institute for Advanced Research 10 class (CIFAR-10) dataset from 92.0% to 93.0% and from 30.5% to 34.9%, respectively. We then propose a new model referred to as a Neural Network with Quantum Entanglement (NNQE) using a strongly entangled quantum circuit combined with Hadamard gates. The new model further improves the image classification accuracy of MNIST and CIFAR-10 to 93.8% and 36.0%, respectively. Unlike other QML methods, the proposed method does not require optimization of the parameters inside the quantum circuits; hence, it requires only limited use of the quantum circuit. Given the small number of qubits and relatively shallow depth of the proposed quantum circuit, the proposed method is well suited for implementation in noisy intermediate-scale quantum computers. While promising results were obtained by the proposed method when applied to the MNIST and CIFAR-10 datasets, a test against a more complicated German Traffic Sign Recognition Benchmark (GTSRB) dataset degraded the image classification accuracy from 82.2% to 73.4%. The exact causes of the performance improvement and degradation are currently an open question, prompting further research on the understanding and design of suitable quantum circuits for image classification neural networks for colored and complex data.
format Online
Article
Text
id pubmed-10007163
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100071632023-03-12 Accurate Image Multi-Class Classification Neural Network Model with Quantum Entanglement Approach Riaz, Farina Abdulla, Shahab Suzuki, Hajime Ganguly, Srinjoy Deo, Ravinesh C. Hopkins, Susan Sensors (Basel) Communication Quantum machine learning (QML) has attracted significant research attention over the last decade. Multiple models have been developed to demonstrate the practical applications of the quantum properties. In this study, we first demonstrate that the previously proposed quanvolutional neural network (QuanvNN) using a randomly generated quantum circuit improves the image classification accuracy of a fully connected neural network against the Modified National Institute of Standards and Technology (MNIST) dataset and the Canadian Institute for Advanced Research 10 class (CIFAR-10) dataset from 92.0% to 93.0% and from 30.5% to 34.9%, respectively. We then propose a new model referred to as a Neural Network with Quantum Entanglement (NNQE) using a strongly entangled quantum circuit combined with Hadamard gates. The new model further improves the image classification accuracy of MNIST and CIFAR-10 to 93.8% and 36.0%, respectively. Unlike other QML methods, the proposed method does not require optimization of the parameters inside the quantum circuits; hence, it requires only limited use of the quantum circuit. Given the small number of qubits and relatively shallow depth of the proposed quantum circuit, the proposed method is well suited for implementation in noisy intermediate-scale quantum computers. While promising results were obtained by the proposed method when applied to the MNIST and CIFAR-10 datasets, a test against a more complicated German Traffic Sign Recognition Benchmark (GTSRB) dataset degraded the image classification accuracy from 82.2% to 73.4%. The exact causes of the performance improvement and degradation are currently an open question, prompting further research on the understanding and design of suitable quantum circuits for image classification neural networks for colored and complex data. MDPI 2023-03-02 /pmc/articles/PMC10007163/ /pubmed/36904951 http://dx.doi.org/10.3390/s23052753 Text en © 2023 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 Communication
Riaz, Farina
Abdulla, Shahab
Suzuki, Hajime
Ganguly, Srinjoy
Deo, Ravinesh C.
Hopkins, Susan
Accurate Image Multi-Class Classification Neural Network Model with Quantum Entanglement Approach
title Accurate Image Multi-Class Classification Neural Network Model with Quantum Entanglement Approach
title_full Accurate Image Multi-Class Classification Neural Network Model with Quantum Entanglement Approach
title_fullStr Accurate Image Multi-Class Classification Neural Network Model with Quantum Entanglement Approach
title_full_unstemmed Accurate Image Multi-Class Classification Neural Network Model with Quantum Entanglement Approach
title_short Accurate Image Multi-Class Classification Neural Network Model with Quantum Entanglement Approach
title_sort accurate image multi-class classification neural network model with quantum entanglement approach
topic Communication
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007163/
https://www.ncbi.nlm.nih.gov/pubmed/36904951
http://dx.doi.org/10.3390/s23052753
work_keys_str_mv AT riazfarina accurateimagemulticlassclassificationneuralnetworkmodelwithquantumentanglementapproach
AT abdullashahab accurateimagemulticlassclassificationneuralnetworkmodelwithquantumentanglementapproach
AT suzukihajime accurateimagemulticlassclassificationneuralnetworkmodelwithquantumentanglementapproach
AT gangulysrinjoy accurateimagemulticlassclassificationneuralnetworkmodelwithquantumentanglementapproach
AT deoravineshc accurateimagemulticlassclassificationneuralnetworkmodelwithquantumentanglementapproach
AT hopkinssusan accurateimagemulticlassclassificationneuralnetworkmodelwithquantumentanglementapproach