DC Field | Value | Language |
---|---|---|
dc.contributor.author | Blank, Carsten | ko |
dc.contributor.author | Rhee, June-Koo Kevin | ko |
dc.contributor.author | Park, Kyungdeok | ko |
dc.contributor.author | Petruccione, Francesco | ko |
dc.date.accessioned | 2019-12-13T08:35:55Z | - |
dc.date.available | 2019-12-13T08:35:55Z | - |
dc.date.created | 2019-11-27 | - |
dc.date.issued | 2019-10-23 | - |
dc.identifier.citation | Quantum Techniques in Machine Learning (QTML) 2019, pp.57 - 58 | - |
dc.identifier.uri | http://hdl.handle.net/10203/269187 | - |
dc.description.abstract | We propose a distance-based quantum supervised learning protocol that implements a kernel based on the quantum state fidelity between training and test data. In principle, a swap-test with the test datum and an entangled state, that encodes training and label data in a specific form, followed by measuring an expectation value of a two-qubit observable, which takes the combined class label and state-overlap into account, completes the classification. The quantum kernel can be tailored systematically with a quantum circuit to raise the kernel to an arbitrary power and to assign arbitrary weights to each training data. As an interesting finding we document a connection between the proposed classifier and the famous Helstrom measurement for the optimal quantum state discrimination. Finally, we verify our method via classical simulations with a realistic noise model and proof-of-principle experiments using the IBM quantum cloud platform. | - |
dc.language | English | - |
dc.publisher | KAIST | - |
dc.title | Quantum classifier with tailored quantum kernel | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 57 | - |
dc.citation.endingpage | 58 | - |
dc.citation.publicationname | Quantum Techniques in Machine Learning (QTML) 2019 | - |
dc.identifier.conferencecountry | KO | - |
dc.identifier.conferencelocation | Academic Cultural Complex, KAIST | - |
dc.contributor.localauthor | Rhee, June-Koo Kevin | - |
dc.contributor.nonIdAuthor | Blank, Carsten | - |
dc.contributor.nonIdAuthor | Petruccione, Francesco | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.