Cargando…

Generalization Performance of Quantum Metric Learning Classifiers

Quantum computing holds great promise for a number of fields including biology and medicine. A major application in which quantum computers could yield advantage is machine learning, especially kernel-based approaches. A recent method termed quantum metric learning, in which a quantum embedding whic...

Descripción completa

Detalles Bibliográficos
Autores principales: Kim, Jonathan, Bekiranov, Stefan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9687469/
https://www.ncbi.nlm.nih.gov/pubmed/36358927
http://dx.doi.org/10.3390/biom12111576
_version_ 1784836013025132544
author Kim, Jonathan
Bekiranov, Stefan
author_facet Kim, Jonathan
Bekiranov, Stefan
author_sort Kim, Jonathan
collection PubMed
description Quantum computing holds great promise for a number of fields including biology and medicine. A major application in which quantum computers could yield advantage is machine learning, especially kernel-based approaches. A recent method termed quantum metric learning, in which a quantum embedding which maximally separates data into classes is learned, was able to perfectly separate ant and bee image training data. The separation is achieved with an intrinsically quantum objective function and the overall approach was shown to work naturally as a hybrid classical-quantum computation enabling embedding of high dimensional feature data into a small number of qubits. However, the ability of the trained classifier to predict test sample data was never assessed. We assessed the performance of quantum metric learning on test ants and bees image data as well as breast cancer clinical data. We applied the original approach as well as variants in which we performed principal component analysis (PCA) on the feature data to reduce its dimensionality for quantum embedding, thereby limiting the number of model parameters. If the degree of dimensionality reduction was limited and the number of model parameters was constrained to be far less than the number of training samples, we found that quantum metric learning was able to accurately classify test data.
format Online
Article
Text
id pubmed-9687469
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96874692022-11-25 Generalization Performance of Quantum Metric Learning Classifiers Kim, Jonathan Bekiranov, Stefan Biomolecules Article Quantum computing holds great promise for a number of fields including biology and medicine. A major application in which quantum computers could yield advantage is machine learning, especially kernel-based approaches. A recent method termed quantum metric learning, in which a quantum embedding which maximally separates data into classes is learned, was able to perfectly separate ant and bee image training data. The separation is achieved with an intrinsically quantum objective function and the overall approach was shown to work naturally as a hybrid classical-quantum computation enabling embedding of high dimensional feature data into a small number of qubits. However, the ability of the trained classifier to predict test sample data was never assessed. We assessed the performance of quantum metric learning on test ants and bees image data as well as breast cancer clinical data. We applied the original approach as well as variants in which we performed principal component analysis (PCA) on the feature data to reduce its dimensionality for quantum embedding, thereby limiting the number of model parameters. If the degree of dimensionality reduction was limited and the number of model parameters was constrained to be far less than the number of training samples, we found that quantum metric learning was able to accurately classify test data. MDPI 2022-10-27 /pmc/articles/PMC9687469/ /pubmed/36358927 http://dx.doi.org/10.3390/biom12111576 Text en © 2022 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 Article
Kim, Jonathan
Bekiranov, Stefan
Generalization Performance of Quantum Metric Learning Classifiers
title Generalization Performance of Quantum Metric Learning Classifiers
title_full Generalization Performance of Quantum Metric Learning Classifiers
title_fullStr Generalization Performance of Quantum Metric Learning Classifiers
title_full_unstemmed Generalization Performance of Quantum Metric Learning Classifiers
title_short Generalization Performance of Quantum Metric Learning Classifiers
title_sort generalization performance of quantum metric learning classifiers
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9687469/
https://www.ncbi.nlm.nih.gov/pubmed/36358927
http://dx.doi.org/10.3390/biom12111576
work_keys_str_mv AT kimjonathan generalizationperformanceofquantummetriclearningclassifiers
AT bekiranovstefan generalizationperformanceofquantummetriclearningclassifiers