Quantum error-correcting output codes
Article
Windridge, D., Mengoni, R. and Nagarajan, R. 2018. Quantum error-correcting output codes. International Journal of Quantum Information. 16 (8). https://doi.org/10.1142/S0219749918400038
Type | Article |
---|---|
Title | Quantum error-correcting output codes |
Authors | Windridge, D., Mengoni, R. and Nagarajan, R. |
Abstract | Quantum machine learning is the aspect of quantum computing concerned with the design of algorithms capable of generalized learning from labeled training data by effectively exploiting quantum effects. Error-correcting output codes (ECOC) are a standard setting in machine learning for efficiently rendering the collective outputs of a binary classifier, such as the support vector machine, as a multi-class decision procedure. Appropriate choice of error-correcting codes further enables incorrect individual classification decisions to be effectively corrected in the composite output. In this paper, we propose an appropriate quantization of the ECOC process, based on the quantum support vector machine. We will show that, in addition to the usual benefits of quantizing machine learning, this technique leads to an exponential reduction in the number of logic gates required for effective correction of classification error. |
Keywords | Quantum machine learning; error-correcting output codes; support vector machines |
Research Group | Foundations of Computing group |
Publisher | World Scientific Publishing |
Journal | International Journal of Quantum Information |
ISSN | 0219-7499 |
Electronic | 1793-6918 |
Publication dates | |
Online | 15 Aug 2018 |
01 Dec 2018 | |
Publication process dates | |
Deposited | 29 Aug 2018 |
Accepted | 24 Jun 2018 |
Output status | Published |
Accepted author manuscript | |
Copyright Statement | Electronic version of an article published as International Journal of Quantum Information, Vol. 16, No. 08, 2018, Article DOI: https://doi.org/10.1142/S0219749918400038 © 2018 World Scientific Publishing Company. Journal URL: https://www.worldscientific.com/worldscinet/ijqi |
Digital Object Identifier (DOI) | https://doi.org/10.1142/S0219749918400038 |
Scopus EID | 2-s2.0-85052966708 |
Web of Science identifier | WOS:000453520000004 |
Related Output | |
Has metadata | http://www.scopus.com/inward/record.url?eid=2-s2.0-85052966708&partnerID=MN8TOARS |
Language | English |
https://repository.mdx.ac.uk/item/87wy9
Download files
58
total views14
total downloads0
views this month1
downloads this month