Quantum learning without quantum memory

A quantum learning machine for binary classification of qubit states that does not require quantum memory is introduced and shown to perform with the minimum error rate allowed by quantum mechanics for any size of the training set. This result is shown to be robust under (an arbitrary amount of) noi...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2012-10, Vol.2 (1), p.708-708, Article 708
Main Authors: Sentís, G., Calsamiglia, J., Muñoz-Tapia, R., Bagan, E.
Format: Article
Language:English
Subjects:
639/624/400/482
639/705/531
639/766/259
639/766/483
Artificial Intelligence
Automatic Data Processing
CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSICS
Classification
Humanities and Social Sciences
Humans
Information theory and computation
Learning
Learning algorithms
Memory
multidisciplinary
Quantum optics
Quantum physics
Quantum Theory
Science
Statistics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A quantum learning machine for binary classification of qubit states that does not require quantum memory is introduced and shown to perform with the minimum error rate allowed by quantum mechanics for any size of the training set. This result is shown to be robust under (an arbitrary amount of) noise and under (statistical) variations in the composition of the training set, provided it is large enough. This machine can be used an arbitrary number of times without retraining. Its required classical memory grows only logarithmically with the number of training qubits, while its excess risk decreases as the inverse of this number and twice as fast as the excess risk of an “estimate-and-discriminate” machine, which estimates the states of the training qubits and classifies the data qubit with a discrimination protocol tailored to the obtained estimates.
ISSN:2045-2322
2045-2322
DOI:10.1038/srep00708