Pipicelli, Claudio (2020) Quantum Machine Learning: A Comparison Between Quantum and Classical Support Vector Machine. [Tesi di dottorato]

[img]
Preview
Text
PhDThesisPipicelliFinal.pdf

Download (19MB) | Preview
[error in script] [error in script]
Item Type: Tesi di dottorato
Resource language: English
Title: Quantum Machine Learning: A Comparison Between Quantum and Classical Support Vector Machine
Creators:
CreatorsEmail
Pipicelli, Claudioclaudio.pipicelli@unina.it
Date: 10 June 2020
Number of Pages: 205
Institution: Università degli Studi di Napoli Federico II
Department: Matematica e Applicazioni "Renato Caccioppoli"
Dottorato: Scienze matematiche e informatiche
Ciclo di dottorato: 32
Coordinatore del Corso di dottorato:
nomeemail
de Giovanni, Francescodegiovan@unina.it
Tutor:
nomeemail
Benerecetti, MassimoUNSPECIFIED
Date: 10 June 2020
Number of Pages: 205
Keywords: Quantum Machine Learning,Quantum Support Vector Machine
Settori scientifico-disciplinari del MIUR: Area 01 - Scienze matematiche e informatiche > INF/01 - Informatica
Date Deposited: 13 Jun 2020 07:44
Last Modified: 28 Oct 2021 12:22
URI: http://www.fedoa.unina.it/id/eprint/13259

Collection description

This thesis is mainly focused on the study of Quantum Support Vector Machine (QSVM), a very important member of the recent and innovative Quantum Machine Learning field, and its comparison with conventional Support Vector Machine (SVM). In this paper, I have worked on the application of Quantum Support Vector Machine algorithm, that runs on near term quantum processors from I.B.M., through IBM Quantum Experience cloud service, to a set of supervised machine learning case studies and I compared its performance with classical Support Vector Machine algorithm; net of the enormous hype surrounding the proliferation of quantum technologies in recent years, are we beginning to glimpse an application of real interest in which quantum systems, albeit with limitations, offer concrete improvements already now?

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item