Cargando…

Quantum machine learning: a classical perspective

Recently, increased computational power and data availability, as well as algorithmic advances, have led machine learning (ML) techniques to impressive results in regression, classification, data generation and reinforcement learning tasks. Despite these successes, the proximity to the physical limi...

Descripción completa

Detalles Bibliográficos
Autores principales: Ciliberto, Carlo, Herbster, Mark, Ialongo, Alessandro Davide, Pontil, Massimiliano, Rocchetto, Andrea, Severini, Simone, Wossnig, Leonard
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Royal Society Publishing 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5806018/
https://www.ncbi.nlm.nih.gov/pubmed/29434508
http://dx.doi.org/10.1098/rspa.2017.0551
_version_ 1783299059138691072
author Ciliberto, Carlo
Herbster, Mark
Ialongo, Alessandro Davide
Pontil, Massimiliano
Rocchetto, Andrea
Severini, Simone
Wossnig, Leonard
author_facet Ciliberto, Carlo
Herbster, Mark
Ialongo, Alessandro Davide
Pontil, Massimiliano
Rocchetto, Andrea
Severini, Simone
Wossnig, Leonard
author_sort Ciliberto, Carlo
collection PubMed
description Recently, increased computational power and data availability, as well as algorithmic advances, have led machine learning (ML) techniques to impressive results in regression, classification, data generation and reinforcement learning tasks. Despite these successes, the proximity to the physical limits of chip fabrication alongside the increasing size of datasets is motivating a growing number of researchers to explore the possibility of harnessing the power of quantum computation to speed up classical ML algorithms. Here we review the literature in quantum ML and discuss perspectives for a mixed readership of classical ML and quantum computation experts. Particular emphasis will be placed on clarifying the limitations of quantum algorithms, how they compare with their best classical counterparts and why quantum resources are expected to provide advantages for learning problems. Learning in the presence of noise and certain computationally hard problems in ML are identified as promising directions for the field. Practical questions, such as how to upload classical data into quantum form, will also be addressed.
format Online
Article
Text
id pubmed-5806018
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher The Royal Society Publishing
record_format MEDLINE/PubMed
spelling pubmed-58060182018-02-12 Quantum machine learning: a classical perspective Ciliberto, Carlo Herbster, Mark Ialongo, Alessandro Davide Pontil, Massimiliano Rocchetto, Andrea Severini, Simone Wossnig, Leonard Proc Math Phys Eng Sci Review Articles Recently, increased computational power and data availability, as well as algorithmic advances, have led machine learning (ML) techniques to impressive results in regression, classification, data generation and reinforcement learning tasks. Despite these successes, the proximity to the physical limits of chip fabrication alongside the increasing size of datasets is motivating a growing number of researchers to explore the possibility of harnessing the power of quantum computation to speed up classical ML algorithms. Here we review the literature in quantum ML and discuss perspectives for a mixed readership of classical ML and quantum computation experts. Particular emphasis will be placed on clarifying the limitations of quantum algorithms, how they compare with their best classical counterparts and why quantum resources are expected to provide advantages for learning problems. Learning in the presence of noise and certain computationally hard problems in ML are identified as promising directions for the field. Practical questions, such as how to upload classical data into quantum form, will also be addressed. The Royal Society Publishing 2018-01 2018-01-17 /pmc/articles/PMC5806018/ /pubmed/29434508 http://dx.doi.org/10.1098/rspa.2017.0551 Text en © 2018 The Authors. http://creativecommons.org/licenses/by/4.0/ Published by the Royal Society under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/4.0/, which permits unrestricted use, provided the original author and source are credited.
spellingShingle Review Articles
Ciliberto, Carlo
Herbster, Mark
Ialongo, Alessandro Davide
Pontil, Massimiliano
Rocchetto, Andrea
Severini, Simone
Wossnig, Leonard
Quantum machine learning: a classical perspective
title Quantum machine learning: a classical perspective
title_full Quantum machine learning: a classical perspective
title_fullStr Quantum machine learning: a classical perspective
title_full_unstemmed Quantum machine learning: a classical perspective
title_short Quantum machine learning: a classical perspective
title_sort quantum machine learning: a classical perspective
topic Review Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5806018/
https://www.ncbi.nlm.nih.gov/pubmed/29434508
http://dx.doi.org/10.1098/rspa.2017.0551
work_keys_str_mv AT cilibertocarlo quantummachinelearningaclassicalperspective
AT herbstermark quantummachinelearningaclassicalperspective
AT ialongoalessandrodavide quantummachinelearningaclassicalperspective
AT pontilmassimiliano quantummachinelearningaclassicalperspective
AT rocchettoandrea quantummachinelearningaclassicalperspective
AT severinisimone quantummachinelearningaclassicalperspective
AT wossnigleonard quantummachinelearningaclassicalperspective