ResQNets: a residual approach for mitigating barren plateaus in quantum neural networks

<p dir="ltr">The barren plateau problem in quantum neural networks (QNNs) is a significant challenge that hinders the practical success of QNNs. In this paper, we introduce residual quantum neural networks (ResQNets) as a solution to address this problem. ResQNets are inspired by cla...

Full description

Saved in:
Bibliographic Details
Main Author: Muhammad Kashif (3923483) (author)
Other Authors: Saif Al-Kuwari (16904610) (author)
Published: 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513510664306688
author Muhammad Kashif (3923483)
author2 Saif Al-Kuwari (16904610)
author2_role author
author_facet Muhammad Kashif (3923483)
Saif Al-Kuwari (16904610)
author_role author
dc.creator.none.fl_str_mv Muhammad Kashif (3923483)
Saif Al-Kuwari (16904610)
dc.date.none.fl_str_mv 2024-01-10T09:00:00Z
dc.identifier.none.fl_str_mv 10.1140/epjqt/s40507-023-00216-8
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/ResQNets_a_residual_approach_for_mitigating_barren_plateaus_in_quantum_neural_networks/26325040
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Machine learning
Theory of computation
Quantum neural networks
Barren plateaus
Parameterized quantum circuits
Residual learning
dc.title.none.fl_str_mv ResQNets: a residual approach for mitigating barren plateaus in quantum neural networks
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">The barren plateau problem in quantum neural networks (QNNs) is a significant challenge that hinders the practical success of QNNs. In this paper, we introduce residual quantum neural networks (ResQNets) as a solution to address this problem. ResQNets are inspired by classical residual neural networks and involve splitting the conventional QNN architecture into multiple quantum nodes, each containing its own parameterized quantum circuit, and introducing residual connections between these nodes. Our study demonstrates the efficacy of ResQNets by comparing their performance with that of conventional QNNs and plain quantum neural networks through multiple training experiments and analyzing the cost function landscapes. Our results show that the incorporation of residual connections results in improved training performance. Therefore, we conclude that ResQNets offer a promising solution to overcome the barren plateau problem in QNNs and provide a potential direction for future research in the field of quantum machine learning.</p><h2>Other Information</h2><p dir="ltr">Published in: EPJ Quantum Technology<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1140/epjqt/s40507-023-00216-8" target="_blank">https://dx.doi.org/10.1140/epjqt/s40507-023-00216-8</a></p>
eu_rights_str_mv openAccess
id Manara2_1ca5787b18a624b7b57be0f484f28e7d
identifier_str_mv 10.1140/epjqt/s40507-023-00216-8
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/26325040
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling ResQNets: a residual approach for mitigating barren plateaus in quantum neural networksMuhammad Kashif (3923483)Saif Al-Kuwari (16904610)Information and computing sciencesMachine learningTheory of computationQuantum neural networksBarren plateausParameterized quantum circuitsResidual learning<p dir="ltr">The barren plateau problem in quantum neural networks (QNNs) is a significant challenge that hinders the practical success of QNNs. In this paper, we introduce residual quantum neural networks (ResQNets) as a solution to address this problem. ResQNets are inspired by classical residual neural networks and involve splitting the conventional QNN architecture into multiple quantum nodes, each containing its own parameterized quantum circuit, and introducing residual connections between these nodes. Our study demonstrates the efficacy of ResQNets by comparing their performance with that of conventional QNNs and plain quantum neural networks through multiple training experiments and analyzing the cost function landscapes. Our results show that the incorporation of residual connections results in improved training performance. Therefore, we conclude that ResQNets offer a promising solution to overcome the barren plateau problem in QNNs and provide a potential direction for future research in the field of quantum machine learning.</p><h2>Other Information</h2><p dir="ltr">Published in: EPJ Quantum Technology<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1140/epjqt/s40507-023-00216-8" target="_blank">https://dx.doi.org/10.1140/epjqt/s40507-023-00216-8</a></p>2024-01-10T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1140/epjqt/s40507-023-00216-8https://figshare.com/articles/journal_contribution/ResQNets_a_residual_approach_for_mitigating_barren_plateaus_in_quantum_neural_networks/26325040CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/263250402024-01-10T09:00:00Z
spellingShingle ResQNets: a residual approach for mitigating barren plateaus in quantum neural networks
Muhammad Kashif (3923483)
Information and computing sciences
Machine learning
Theory of computation
Quantum neural networks
Barren plateaus
Parameterized quantum circuits
Residual learning
status_str publishedVersion
title ResQNets: a residual approach for mitigating barren plateaus in quantum neural networks
title_full ResQNets: a residual approach for mitigating barren plateaus in quantum neural networks
title_fullStr ResQNets: a residual approach for mitigating barren plateaus in quantum neural networks
title_full_unstemmed ResQNets: a residual approach for mitigating barren plateaus in quantum neural networks
title_short ResQNets: a residual approach for mitigating barren plateaus in quantum neural networks
title_sort ResQNets: a residual approach for mitigating barren plateaus in quantum neural networks
topic Information and computing sciences
Machine learning
Theory of computation
Quantum neural networks
Barren plateaus
Parameterized quantum circuits
Residual learning