Experimental kernel-based quantum machine learning in finite feature space

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989592%3A15310%2F20%3A73602079" target="_blank" >RIV/61989592:15310/20:73602079 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.nature.com/articles/s41598-020-68911-5.pdf" target="_blank" >https://www.nature.com/articles/s41598-020-68911-5.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1038/s41598-020-68911-5" target="_blank" >10.1038/s41598-020-68911-5</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Experimental kernel-based quantum machine learning in finite feature space

Popis výsledku v původním jazyce

We implement an all-optical setup demonstrating kernel-based quantum machine learning for two-dimensional classification problems. In this hybrid approach, kernel evaluations are outsourced to projective measurements on suitably designed quantum states encoding the training data, while the model training is processed on a classical computer. Our two-photon proposal encodes data points in a discrete, eight-dimensional feature Hilbert space. In order to maximize the application range of the deployable kernels, we optimize feature maps towards the resulting kernels&apos; ability to separate points, i.e., their &quot;resolution,&quot; under the constraint of finite, fixed Hilbert space dimension. Implementing these kernels, our setup delivers viable decision boundaries for standard nonlinear supervised classification tasks in feature space. We demonstrate such kernel-based quantum machine learning using specialized multiphoton quantum optical circuits. The deployed kernel exhibits exponentially better scaling in the required number of qubits than a direct generalization of kernels described in the literature.

Název v anglickém jazyce

Experimental kernel-based quantum machine learning in finite feature space

Popis výsledku anglicky

We implement an all-optical setup demonstrating kernel-based quantum machine learning for two-dimensional classification problems. In this hybrid approach, kernel evaluations are outsourced to projective measurements on suitably designed quantum states encoding the training data, while the model training is processed on a classical computer. Our two-photon proposal encodes data points in a discrete, eight-dimensional feature Hilbert space. In order to maximize the application range of the deployable kernels, we optimize feature maps towards the resulting kernels&apos; ability to separate points, i.e., their &quot;resolution,&quot; under the constraint of finite, fixed Hilbert space dimension. Implementing these kernels, our setup delivers viable decision boundaries for standard nonlinear supervised classification tasks in feature space. We demonstrate such kernel-based quantum machine learning using specialized multiphoton quantum optical circuits. The deployed kernel exhibits exponentially better scaling in the required number of qubits than a direct generalization of kernels described in the literature.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10306 - Optics (including laser optics and quantum optics)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Scientific Reports

ISSN

2045-2322

e-ISSN

—

Svazek periodika

10

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

9

Strana od-do

"12356-1"-"12356-9"

Kód UT WoS článku

000556690900063

EID výsledku v databázi Scopus

2-s2.0-85088502642