The unified effect of data encoding, ansatz expressibility and entanglement on the trainability of HQNNs

<p dir="ltr">Recent advances in quantum computing and machine learning have brought about a promising intersection of these two fields, leading to the emergence of quantum machine learning (QML). However, the integration of quantum computing and machine learning poses several challen...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Muhammad Kashif (3923483) (author)
مؤلفون آخرون: Saif Al-Kuwari (16904610) (author)
منشور في: 2023
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513527919673344
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 2023-07-17T03:00:00Z
dc.identifier.none.fl_str_mv 10.1080/17445760.2023.2231163
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/The_unified_effect_of_data_encoding_ansatz_expressibility_and_entanglement_on_the_trainability_of_HQNNs/25187612
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
Artificial intelligence
Data management and data science
Machine learning
Quantum machine learning
entanglement
data encoding
quantum neural networks
trainability
dc.title.none.fl_str_mv The unified effect of data encoding, ansatz expressibility and entanglement on the trainability of HQNNs
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Recent advances in quantum computing and machine learning have brought about a promising intersection of these two fields, leading to the emergence of quantum machine learning (QML). However, the integration of quantum computing and machine learning poses several challenges. One of the prominent challenges lies in the presence of barren plateaus (BP) in QML algorithms, particularly in quantum neural networks (QNNs). Recent studies have successfully identified the fundamental causes underlying the existence of BP in QNNs. This paper presents a framework designed to explore the interplay of multiple factors contributing to the BP problem in quantum neural networks (QNNs), which poses a critical challenge for the practical applications of QML. We focus on the combined influence of data encoding, qubit entanglement, and ansatz expressibility in hybrid quantum neural networks (HQNNs) for multi-class classification tasks. Our framework aims to empirically analyze the joint impact of these factors on the training landscape of HQNNs. Our results show that the occurrence of the BP problem in HQNNs is contingent upon the expressibility of the underlying ansatz and the type of the adopted data encoding technique. Additionally, we observe that qubit entanglement also plays a role in exacerbating the BP problem. Leveraging various evaluation metrics for classification tasks, we systematically evaluate the performance of HQNNs and provide recommendations tailored to different constraint scenarios. Our findings emphasize the significance of our framework in addressing the practical success of QNNs.</p><h2>Other Information</h2><p dir="ltr">Published in: International Journal of Parallel, Emergent and Distributed Systems<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1080/17445760.2023.2231163" target="_blank">https://dx.doi.org/10.1080/17445760.2023.2231163</a></p>
eu_rights_str_mv openAccess
id Manara2_30c1a798a23246b9f359bc7dd8d565be
identifier_str_mv 10.1080/17445760.2023.2231163
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25187612
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling The unified effect of data encoding, ansatz expressibility and entanglement on the trainability of HQNNsMuhammad Kashif (3923483)Saif Al-Kuwari (16904610)Information and computing sciencesArtificial intelligenceData management and data scienceMachine learningQuantum machine learningentanglementdata encodingquantum neural networkstrainability<p dir="ltr">Recent advances in quantum computing and machine learning have brought about a promising intersection of these two fields, leading to the emergence of quantum machine learning (QML). However, the integration of quantum computing and machine learning poses several challenges. One of the prominent challenges lies in the presence of barren plateaus (BP) in QML algorithms, particularly in quantum neural networks (QNNs). Recent studies have successfully identified the fundamental causes underlying the existence of BP in QNNs. This paper presents a framework designed to explore the interplay of multiple factors contributing to the BP problem in quantum neural networks (QNNs), which poses a critical challenge for the practical applications of QML. We focus on the combined influence of data encoding, qubit entanglement, and ansatz expressibility in hybrid quantum neural networks (HQNNs) for multi-class classification tasks. Our framework aims to empirically analyze the joint impact of these factors on the training landscape of HQNNs. Our results show that the occurrence of the BP problem in HQNNs is contingent upon the expressibility of the underlying ansatz and the type of the adopted data encoding technique. Additionally, we observe that qubit entanglement also plays a role in exacerbating the BP problem. Leveraging various evaluation metrics for classification tasks, we systematically evaluate the performance of HQNNs and provide recommendations tailored to different constraint scenarios. Our findings emphasize the significance of our framework in addressing the practical success of QNNs.</p><h2>Other Information</h2><p dir="ltr">Published in: International Journal of Parallel, Emergent and Distributed Systems<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1080/17445760.2023.2231163" target="_blank">https://dx.doi.org/10.1080/17445760.2023.2231163</a></p>2023-07-17T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1080/17445760.2023.2231163https://figshare.com/articles/journal_contribution/The_unified_effect_of_data_encoding_ansatz_expressibility_and_entanglement_on_the_trainability_of_HQNNs/25187612CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/251876122023-07-17T03:00:00Z
spellingShingle The unified effect of data encoding, ansatz expressibility and entanglement on the trainability of HQNNs
Muhammad Kashif (3923483)
Information and computing sciences
Artificial intelligence
Data management and data science
Machine learning
Quantum machine learning
entanglement
data encoding
quantum neural networks
trainability
status_str publishedVersion
title The unified effect of data encoding, ansatz expressibility and entanglement on the trainability of HQNNs
title_full The unified effect of data encoding, ansatz expressibility and entanglement on the trainability of HQNNs
title_fullStr The unified effect of data encoding, ansatz expressibility and entanglement on the trainability of HQNNs
title_full_unstemmed The unified effect of data encoding, ansatz expressibility and entanglement on the trainability of HQNNs
title_short The unified effect of data encoding, ansatz expressibility and entanglement on the trainability of HQNNs
title_sort The unified effect of data encoding, ansatz expressibility and entanglement on the trainability of HQNNs
topic Information and computing sciences
Artificial intelligence
Data management and data science
Machine learning
Quantum machine learning
entanglement
data encoding
quantum neural networks
trainability