Multi-class classification based on quantum state discrimination

We present a general framework for the problem of multi-class classification using classification functions that can be interpreted as fuzzy sets. We specialize these functions in the domain of Quantum-inspired classifiers, which are based on quantum state discrimination techniques. In particular, w...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Giuntini, Roberto, Granda Arango, Andrés Camilo, Freytes, Hector, Holik, Federico Hernán, Sergioli, Giuseppe
Formato: Articulo
Lenguaje:Inglés
Publicado: 2023
Materias:
Física
Quantum-inspired algorithms
Multi-class classification
Pretty Good Measurement
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/159869
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-159869
record_format dspace
spelling I19-R120-10915-1598692023-11-07T20:07:15Z http://sedici.unlp.edu.ar/handle/10915/159869 Multi-class classification based on quantum state discrimination Giuntini, Roberto Granda Arango, Andrés Camilo Freytes, Hector Holik, Federico Hernán Sergioli, Giuseppe 2023 2023-11-07T15:08:10Z en Física Quantum-inspired algorithms Multi-class classification Pretty Good Measurement We present a general framework for the problem of multi-class classification using classification functions that can be interpreted as fuzzy sets. We specialize these functions in the domain of Quantum-inspired classifiers, which are based on quantum state discrimination techniques. In particular, we use unsharp observables (Positive Operator-Valued Measures) that are determined by the training set of a given dataset to construct these classification functions. We show that such classifiers can be tested on near-term quantum computers once these classification functions are “distilled” (on a classical platform) from the quantum encoding of a training dataset. We compare these experimental results with their theoretical counterparts and we pose some questions for future research. Instituto de Física La Plata Articulo Articulo http://creativecommons.org/licenses/by/4.0/ Creative Commons Attribution 4.0 International (CC BY 4.0) application/pdf
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Física
Quantum-inspired algorithms
Multi-class classification
Pretty Good Measurement
spellingShingle Física
Quantum-inspired algorithms
Multi-class classification
Pretty Good Measurement
Giuntini, Roberto
Granda Arango, Andrés Camilo
Freytes, Hector
Holik, Federico Hernán
Sergioli, Giuseppe
Multi-class classification based on quantum state discrimination
topic_facet Física
Quantum-inspired algorithms
Multi-class classification
Pretty Good Measurement
description We present a general framework for the problem of multi-class classification using classification functions that can be interpreted as fuzzy sets. We specialize these functions in the domain of Quantum-inspired classifiers, which are based on quantum state discrimination techniques. In particular, we use unsharp observables (Positive Operator-Valued Measures) that are determined by the training set of a given dataset to construct these classification functions. We show that such classifiers can be tested on near-term quantum computers once these classification functions are “distilled” (on a classical platform) from the quantum encoding of a training dataset. We compare these experimental results with their theoretical counterparts and we pose some questions for future research.
format Articulo
Articulo
author Giuntini, Roberto
Granda Arango, Andrés Camilo
Freytes, Hector
Holik, Federico Hernán
Sergioli, Giuseppe
author_facet Giuntini, Roberto
Granda Arango, Andrés Camilo
Freytes, Hector
Holik, Federico Hernán
Sergioli, Giuseppe
author_sort Giuntini, Roberto
title Multi-class classification based on quantum state discrimination
title_short Multi-class classification based on quantum state discrimination
title_full Multi-class classification based on quantum state discrimination
title_fullStr Multi-class classification based on quantum state discrimination
title_full_unstemmed Multi-class classification based on quantum state discrimination
title_sort multi-class classification based on quantum state discrimination
publishDate 2023
url http://sedici.unlp.edu.ar/handle/10915/159869
work_keys_str_mv AT giuntiniroberto multiclassclassificationbasedonquantumstatediscrimination
AT grandaarangoandrescamilo multiclassclassificationbasedonquantumstatediscrimination
AT freyteshector multiclassclassificationbasedonquantumstatediscrimination
AT holikfedericohernan multiclassclassificationbasedonquantumstatediscrimination
AT sergioligiuseppe multiclassclassificationbasedonquantumstatediscrimination
_version_ 1807221782964338688

Ejemplares similares