Neural Networks with Variational Quantum Circuits

Syed Muhammad Abuzar Rizvi; Muhammad Shohibul Ulum; Naema Asif; Hyundong Shin

doi:10.1007/978-3-031-47359-3_15

Neural Networks with Variational Quantum Circuits

Syed Muhammad Abuzar Rizvi
, Muhammad Shohibul Ulum
, Naema Asif
, Hyundong Shin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Citations (Scopus)

Abstract

The field of machine learning is an interdisciplinary area that aims to extract useful information from data through mathematical means. Integrating quantum computing with machine learning has led to exciting new avenues of research, where quantum mechanics principles are applied to enhance and optimize classical machine learning algorithms. In this study, we explore hybrid quantum-classical neural networks with an approach that combines both classical and quantum computing. We achieve this by implementing a variational quantum circuit as the output layer of a classical convolutional neural network. We use this hybrid neural network to classify images of digits from the MNIST dataset. Using this approach, we were able to classify images with high accuracy. Furthermore, due to its flexibility, this hybrid algorithm can be adapted to explore the potential of quantum computing especially in the era of noisy intermediate-scale quantum devices.

Original language	English
Title of host publication	Industrial Networks and Intelligent Systems - 9th EAI International Conference, INISCOM 2023, Proceedings
Editors	Nguyen-Son Vo, Hoai-An Tran
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	203-214
Number of pages	12
ISBN (Print)	9783031473586
DOIs	https://doi.org/10.1007/978-3-031-47359-3_15
Publication status	Published - 2023
Event	9th EAI International Conference on Industrial Networks and Intelligent Systems, INISCOM 2023 - Ho Chi Minh City, Viet Nam Duration: 2 Aug 2023 → 3 Aug 2023

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume	531
ISSN (Print)	1867-8211
ISSN (Electronic)	1867-822X

Conference

Conference	9th EAI International Conference on Industrial Networks and Intelligent Systems, INISCOM 2023
Country/Territory	Viet Nam
City	Ho Chi Minh City
Period	2/08/23 → 3/08/23

Bibliographical note

Publisher Copyright:
© 2023, © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Keywords

Image Classification
Neural Networks
Quantum Computing
Variational Quantum Circuits

Access to Document

10.1007/978-3-031-47359-3_15

Cite this

Rizvi, S. M. A., Ulum, M. S., Asif, N., & Shin, H. (2023). Neural Networks with Variational Quantum Circuits. In N.-S. Vo, & H.-A. Tran (Eds.), Industrial Networks and Intelligent Systems - 9th EAI International Conference, INISCOM 2023, Proceedings (pp. 203-214). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 531). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-47359-3_15

Rizvi, Syed Muhammad Abuzar ; Ulum, Muhammad Shohibul ; Asif, Naema et al. / Neural Networks with Variational Quantum Circuits. Industrial Networks and Intelligent Systems - 9th EAI International Conference, INISCOM 2023, Proceedings. editor / Nguyen-Son Vo ; Hoai-An Tran. Springer Science and Business Media Deutschland GmbH, 2023. pp. 203-214 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST).

@inproceedings{2527d2b76f5445ab81fffcdbe603b039,

title = "Neural Networks with Variational Quantum Circuits",

abstract = "The field of machine learning is an interdisciplinary area that aims to extract useful information from data through mathematical means. Integrating quantum computing with machine learning has led to exciting new avenues of research, where quantum mechanics principles are applied to enhance and optimize classical machine learning algorithms. In this study, we explore hybrid quantum-classical neural networks with an approach that combines both classical and quantum computing. We achieve this by implementing a variational quantum circuit as the output layer of a classical convolutional neural network. We use this hybrid neural network to classify images of digits from the MNIST dataset. Using this approach, we were able to classify images with high accuracy. Furthermore, due to its flexibility, this hybrid algorithm can be adapted to explore the potential of quantum computing especially in the era of noisy intermediate-scale quantum devices.",

keywords = "Image Classification, Neural Networks, Quantum Computing, Variational Quantum Circuits",

author = "Rizvi, \{Syed Muhammad Abuzar\} and Ulum, \{Muhammad Shohibul\} and Naema Asif and Hyundong Shin",

note = "Publisher Copyright: {\textcopyright} 2023, {\textcopyright} ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.; 9th EAI International Conference on Industrial Networks and Intelligent Systems, INISCOM 2023 ; Conference date: 02-08-2023 Through 03-08-2023",

year = "2023",

doi = "10.1007/978-3-031-47359-3\_15",

language = "English",

isbn = "9783031473586",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "203--214",

editor = "Nguyen-Son Vo and Hoai-An Tran",

booktitle = "Industrial Networks and Intelligent Systems - 9th EAI International Conference, INISCOM 2023, Proceedings",

address = "Germany",

}

Rizvi, SMA, Ulum, MS, Asif, N & Shin, H 2023, Neural Networks with Variational Quantum Circuits. in N-S Vo & H-A Tran (eds), Industrial Networks and Intelligent Systems - 9th EAI International Conference, INISCOM 2023, Proceedings. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, vol. 531, Springer Science and Business Media Deutschland GmbH, pp. 203-214, 9th EAI International Conference on Industrial Networks and Intelligent Systems, INISCOM 2023, Ho Chi Minh City, Viet Nam, 2/08/23. https://doi.org/10.1007/978-3-031-47359-3_15

Neural Networks with Variational Quantum Circuits. / Rizvi, Syed Muhammad Abuzar; Ulum, Muhammad Shohibul; Asif, Naema et al.
Industrial Networks and Intelligent Systems - 9th EAI International Conference, INISCOM 2023, Proceedings. ed. / Nguyen-Son Vo; Hoai-An Tran. Springer Science and Business Media Deutschland GmbH, 2023. p. 203-214 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 531).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Neural Networks with Variational Quantum Circuits

AU - Rizvi, Syed Muhammad Abuzar

AU - Ulum, Muhammad Shohibul

AU - Asif, Naema

AU - Shin, Hyundong

PY - 2023

Y1 - 2023

N2 - The field of machine learning is an interdisciplinary area that aims to extract useful information from data through mathematical means. Integrating quantum computing with machine learning has led to exciting new avenues of research, where quantum mechanics principles are applied to enhance and optimize classical machine learning algorithms. In this study, we explore hybrid quantum-classical neural networks with an approach that combines both classical and quantum computing. We achieve this by implementing a variational quantum circuit as the output layer of a classical convolutional neural network. We use this hybrid neural network to classify images of digits from the MNIST dataset. Using this approach, we were able to classify images with high accuracy. Furthermore, due to its flexibility, this hybrid algorithm can be adapted to explore the potential of quantum computing especially in the era of noisy intermediate-scale quantum devices.

AB - The field of machine learning is an interdisciplinary area that aims to extract useful information from data through mathematical means. Integrating quantum computing with machine learning has led to exciting new avenues of research, where quantum mechanics principles are applied to enhance and optimize classical machine learning algorithms. In this study, we explore hybrid quantum-classical neural networks with an approach that combines both classical and quantum computing. We achieve this by implementing a variational quantum circuit as the output layer of a classical convolutional neural network. We use this hybrid neural network to classify images of digits from the MNIST dataset. Using this approach, we were able to classify images with high accuracy. Furthermore, due to its flexibility, this hybrid algorithm can be adapted to explore the potential of quantum computing especially in the era of noisy intermediate-scale quantum devices.

KW - Image Classification

KW - Neural Networks

KW - Quantum Computing

KW - Variational Quantum Circuits

UR - https://www.scopus.com/pages/publications/85176933498

U2 - 10.1007/978-3-031-47359-3_15

DO - 10.1007/978-3-031-47359-3_15

M3 - Conference contribution

AN - SCOPUS:85176933498

SN - 9783031473586

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

SP - 203

EP - 214

BT - Industrial Networks and Intelligent Systems - 9th EAI International Conference, INISCOM 2023, Proceedings

A2 - Vo, Nguyen-Son

A2 - Tran, Hoai-An

PB - Springer Science and Business Media Deutschland GmbH

T2 - 9th EAI International Conference on Industrial Networks and Intelligent Systems, INISCOM 2023

Y2 - 2 August 2023 through 3 August 2023

ER -

Rizvi SMA, Ulum MS, Asif N, Shin H. Neural Networks with Variational Quantum Circuits. In Vo NS, Tran HA, editors, Industrial Networks and Intelligent Systems - 9th EAI International Conference, INISCOM 2023, Proceedings. Springer Science and Business Media Deutschland GmbH. 2023. p. 203-214. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST). doi: 10.1007/978-3-031-47359-3_15